{"meta":{"query_hash":"503d7498ec17","filters":{"venue":"Computational Statistics & Data Analysis"},"cohort_total":181,"direct_labels_cover":0,"predictions_cover":181,"exported":181,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/503d7498ec17","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computational+Statistics+%26+Data+Analysis"},"results":[{"id":"W1451216173","doi":"10.1016/j.csda.2015.07.015","title":"Fast and accurate computation for kernel estimators","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Numerical Methods and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Humanities and Social Science Fund of Ministry of Education of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; Univariate; Computation; Algorithm; Kernel (algebra); Grid; Computational complexity theory; Kernel density estimation; Computer science; Multivariate statistics; Mathematics; Computational statistics; Polynomial; Mathematical optimization; Statistics","score_opus":0.1105769333221848,"score_gpt":0.394072255127822,"score_spread":0.2834953218056372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1451216173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017460504,0.00007926762,0.99721116,0.0003575954,0.00013878828,0.00012849768,0.0018237894,0.000063301995,0.000023025941],"genre_scores_gemma":[0.023242094,0.000006287742,0.97324026,0.0001747997,0.00004080638,0.000009631741,0.0032515125,0.00000896938,0.00002566937],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983396,0.00010653258,0.00035450724,0.00060348556,0.0003913957,0.00020449268],"domain_scores_gemma":[0.99775416,0.0009791163,0.00019434845,0.00040978845,0.00041789212,0.0002446918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064054003,0.00015336505,0.0003067436,0.00019803697,0.00015373332,0.00037751376,0.0006229804,0.0000336224,0.000003622624],"category_scores_gemma":[0.0004619315,0.00014553608,0.0000425171,0.0009378959,0.000075040785,0.00050737365,0.00047088624,0.00006832111,0.000011356608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011085341,0.00008106548,0.0016362256,0.000021991968,0.00057810126,0.000010607295,0.00019501288,0.46088699,0.0000015512669,0.11471822,0.008826198,0.41303295],"study_design_scores_gemma":[0.00028830828,0.000040536543,0.009145746,0.000002510318,0.00022629293,0.0000034565944,0.00001128674,0.8269182,6.4263753e-7,0.16256936,0.00064155285,0.00015212511],"about_ca_topic_score_codex":0.00010686033,"about_ca_topic_score_gemma":0.000012010836,"teacher_disagreement_score":0.41288084,"about_ca_system_score_codex":0.00003242569,"about_ca_system_score_gemma":0.00011715803,"threshold_uncertainty_score":0.59347886},"labels":[],"label_agreement":null},{"id":"W1493262437","doi":"10.1016/j.csda.2009.05.020","title":"Distribution-Preserving Statistical Disclosure Limitation","year":2007,"lang":"en","type":"preprint","venue":"Computational Statistics & Data Analysis","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Microdata (statistics); Imputation (statistics); Computer science; Data mining; Limiting; Econometrics; Statistics; Missing data; Mathematics; Machine learning; Engineering","score_opus":0.07166368083739101,"score_gpt":0.35163621995653904,"score_spread":0.27997253911914805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493262437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019841467,0.0003131169,0.86055404,0.003921717,0.00040996374,0.00032147288,0.13354798,0.0006490932,0.00008418522],"genre_scores_gemma":[0.032454517,0.00012197888,0.64912426,0.00010606158,0.00010064657,0.000022725397,0.31801796,0.000027346432,0.000024515324],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992461,0.00037870317,0.0014804666,0.002746109,0.0021242315,0.00080946356],"domain_scores_gemma":[0.9742888,0.0036959,0.0009589269,0.019775428,0.0009811195,0.00029978564],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0020423352,0.0006880725,0.0010055765,0.0008949163,0.0004541636,0.001471646,0.049413197,0.0005209943,0.0001376187],"category_scores_gemma":[0.038844403,0.00075181964,0.00019143075,0.002732264,0.00035683843,0.0010013035,0.2554483,0.0014173425,0.00014396156],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114173135,0.0002172307,0.0064087873,0.0001917236,0.0027310892,0.00016305503,0.00004338351,0.080504045,8.323547e-7,0.13780625,0.754755,0.017167194],"study_design_scores_gemma":[0.000111426714,0.00001263299,0.033678126,0.000029091696,0.00079383416,0.0000030612018,0.0000052802425,0.53806674,0.0000011435604,0.42520717,0.0016746488,0.00041684296],"about_ca_topic_score_codex":0.0006784636,"about_ca_topic_score_gemma":0.00039582804,"teacher_disagreement_score":0.75308037,"about_ca_system_score_codex":0.00043957823,"about_ca_system_score_gemma":0.00061796815,"threshold_uncertainty_score":0.99956495},"labels":[],"label_agreement":null},{"id":"W1512520597","doi":"10.1016/j.csda.2009.07.008","title":"Modified fast double sieve bootstraps for ADF tests","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Sieve (category theory); Mathematics; Unit root; Null (SQL); Null hypothesis; Simple (philosophy); Bootstrap model; Regression; Statistics; Statistical hypothesis testing; Applied mathematics; Algorithm; Computer science; Discrete mathematics; Data mining","score_opus":0.22875077158818644,"score_gpt":0.455635009249989,"score_spread":0.22688423766180257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512520597","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007476758,0.00002878229,0.98016065,0.00024372515,0.000059989106,0.0002879656,0.017811615,0.00006465148,0.0005949656],"genre_scores_gemma":[0.15614818,0.0000071707495,0.8348724,0.00022381767,0.000085223204,0.00001581501,0.008482818,0.000015932137,0.00014865356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977039,0.000086131426,0.0006792196,0.00063401944,0.0005476355,0.00034910208],"domain_scores_gemma":[0.99384964,0.0044186865,0.00027354035,0.0007586745,0.00051469926,0.00018478456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006617242,0.00024621835,0.0005605122,0.00023456868,0.00018237221,0.00016797533,0.00058864616,0.00007723914,0.00027709611],"category_scores_gemma":[0.0020013358,0.00023476731,0.00011260436,0.00078786607,0.000085521264,0.00014018499,0.00010866247,0.00013965757,0.000021216703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007406806,0.00022816533,0.00023591751,0.000041584386,0.0006335311,0.000008139185,0.000060169863,0.012721521,0.0000110087185,0.9151619,0.02641393,0.044410028],"study_design_scores_gemma":[0.00042540903,0.00006568384,0.009559988,0.0000069113926,0.0009979097,0.0000012604378,0.000008523342,0.44456798,0.0000039423758,0.5438185,0.00036737454,0.0001765687],"about_ca_topic_score_codex":0.000060074166,"about_ca_topic_score_gemma":0.00007888933,"teacher_disagreement_score":0.43184647,"about_ca_system_score_codex":0.000045336546,"about_ca_system_score_gemma":0.000112155845,"threshold_uncertainty_score":0.9573533},"labels":[],"label_agreement":null},{"id":"W1553958847","doi":"10.1016/j.csda.2013.06.023","title":"Bayesian Option Pricing Using Mixed Normal Heteroskedasticity Models","year":2009,"lang":"en","type":"preprint","venue":"Computational Statistics & Data Analysis","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations","funders":"Danmarks Grundforskningsfond; National Research Foundation","keywords":"Black–Scholes model; Mathematics; Valuation of options; Econometrics; Gibbs sampling; Economics; Volatility (finance); Bayesian probability; Statistics","score_opus":0.10544698461417648,"score_gpt":0.3010608787808125,"score_spread":0.19561389416663602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553958847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011644393,0.0005323267,0.9568588,0.0000829098,0.00019918357,0.0002683908,0.040671412,0.000053427062,0.00016909059],"genre_scores_gemma":[0.4539249,0.000051072857,0.5208687,0.00007273303,0.00015257971,0.000016312333,0.024881488,0.000022972608,0.0000092376395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682474,0.000017321803,0.0013228089,0.0012852025,0.00018423055,0.0003656931],"domain_scores_gemma":[0.9970997,0.00017904757,0.001220238,0.0010963628,0.00025616252,0.00014847363],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005084157,0.00036874795,0.000944657,0.0006913487,0.00034573668,0.00034038167,0.0009383607,0.00023020072,0.000058536247],"category_scores_gemma":[0.00019713635,0.0004933742,0.0001946025,0.00096525106,0.00008457531,0.000324196,0.000966864,0.00041510077,0.00005051558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005290619,0.00007164148,0.0003160513,0.000044652716,0.00040193042,0.000002149994,0.000038667913,0.5979509,3.0625242e-7,0.4001265,0.00010677547,0.0009351947],"study_design_scores_gemma":[0.00008569718,0.000008010983,0.00641793,0.000013733204,0.00043164022,0.0000010204241,0.0000025256281,0.5185562,1.7045976e-7,0.47418493,0.000043401087,0.00025477752],"about_ca_topic_score_codex":0.001931133,"about_ca_topic_score_gemma":0.0001661381,"teacher_disagreement_score":0.45276046,"about_ca_system_score_codex":0.00024059768,"about_ca_system_score_gemma":0.00016514582,"threshold_uncertainty_score":0.9997518},"labels":[],"label_agreement":null},{"id":"W1554200067","doi":"10.1016/j.csda.2015.04.010","title":"Modelling receiver operating characteristic curves using Gaussian mixtures","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Receiver operating characteristic; Frequentist inference; Gaussian; Monte Carlo method; Parametric statistics; Mathematics; Curve fitting; Parametric equation; Mixture model; Statistics; Algorithm; Computer science; Applied mathematics; Bayesian probability; Bayesian inference; Physics","score_opus":0.29564307459163713,"score_gpt":0.437251055077163,"score_spread":0.14160798048552586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554200067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011349572,0.00017637918,0.9913728,0.00009611198,0.00010786078,0.00014428119,0.006736141,0.000052203308,0.00017923328],"genre_scores_gemma":[0.033780165,0.000042045205,0.96135896,0.00015864152,0.0001233886,0.0000054358607,0.0044657243,0.000028509061,0.00003710622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972359,0.00035969412,0.00074086426,0.0006174569,0.00072987814,0.00031623244],"domain_scores_gemma":[0.99611455,0.0020254166,0.00031819314,0.00068304996,0.00058223226,0.0002765527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010866188,0.00026219882,0.0006165275,0.00022515962,0.00022638838,0.00021352537,0.0005285324,0.0000669818,0.00029781778],"category_scores_gemma":[0.0030823553,0.00024385373,0.0000678702,0.0008333935,0.00011924021,0.0002753119,0.00027491257,0.00021206081,0.00002296131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039648246,0.0002691673,0.004897156,0.00054962694,0.0025569322,0.00014547058,0.00060293305,0.31918377,0.000022585928,0.6368587,0.023143876,0.011730125],"study_design_scores_gemma":[0.00011974904,0.000013599313,0.0005838549,0.000071229726,0.0013004444,0.0000056380163,0.000018004894,0.64583427,0.000001147594,0.3517879,0.000060656213,0.0002035162],"about_ca_topic_score_codex":0.00053006964,"about_ca_topic_score_gemma":0.000032973097,"teacher_disagreement_score":0.32665053,"about_ca_system_score_codex":0.000083733576,"about_ca_system_score_gemma":0.00022703092,"threshold_uncertainty_score":0.99440664},"labels":[],"label_agreement":null},{"id":"W1599092457","doi":"10.1016/j.csda.2013.07.034","title":"Inclusion probabilities in partially rank ordered set sampling","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Rank (graph theory); Variance (accounting); Estimator; Simple random sample; Mathematics; Population; Statistics; Unit (ring theory); Sampling (signal processing); Set (abstract data type); Sampling design; Selection (genetic algorithm); Sample (material); Combinatorics; Computer science; Economics; Artificial intelligence; Demography","score_opus":0.2080757221148221,"score_gpt":0.4147827400347145,"score_spread":0.2067070179198924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599092457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033388056,0.000028801442,0.9638286,0.00022161976,0.00003147653,0.000286655,0.0020237346,0.00014034078,0.000050718027],"genre_scores_gemma":[0.35633278,0.0000096739905,0.6337929,0.000059690352,0.000021705146,0.00003714854,0.009700014,0.000014182826,0.000031930736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978446,0.00022210089,0.0007396733,0.0004474573,0.00050906563,0.00023709773],"domain_scores_gemma":[0.9956606,0.0029769726,0.00022939374,0.00063907396,0.00041739683,0.000076580516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012736253,0.0001801314,0.0004065798,0.0003988018,0.0002710825,0.00015355111,0.00046698676,0.00006908914,0.00058470585],"category_scores_gemma":[0.002584561,0.00017678153,0.00005369907,0.0009254773,0.000077487166,0.00031154754,0.0007706068,0.0001416054,0.000044129454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007935851,0.0009282434,0.13499828,0.000604984,0.0021499554,0.000016920398,0.0054136654,0.4973783,0.000042683736,0.23149168,0.06498962,0.061906334],"study_design_scores_gemma":[0.00012680494,0.000009403718,0.024520528,0.000016104812,0.00015504606,6.069159e-7,0.000028882088,0.47275296,0.0000026468654,0.50211453,0.00014305419,0.00012945075],"about_ca_topic_score_codex":0.0022195086,"about_ca_topic_score_gemma":0.0020151709,"teacher_disagreement_score":0.33003572,"about_ca_system_score_codex":0.000078858204,"about_ca_system_score_gemma":0.00010457436,"threshold_uncertainty_score":0.72089416},"labels":[],"label_agreement":null},{"id":"W1834247060","doi":"10.1016/j.csda.2015.09.009","title":"Testing the order of a population spectral distribution for high-dimensional data","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Covariance; Estimation of covariance matrices; Test statistic; Principal component analysis; Covariance matrix; Eigenvalues and eigenvectors; Population; Asymptotic distribution; Statistics; Consistency (knowledge bases); Applied mathematics; Statistical hypothesis testing; Distribution (mathematics); Mathematical analysis; Physics; Discrete mathematics","score_opus":0.207354647166713,"score_gpt":0.3965675614603455,"score_spread":0.1892129142936325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1834247060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01342451,0.000029245537,0.93504155,0.00030335816,0.000035713565,0.00027419796,0.050859127,0.000021614043,0.000010694953],"genre_scores_gemma":[0.36623806,7.800654e-7,0.49438277,0.000014019027,0.000068695495,0.000009918724,0.13926663,0.000007272214,0.000011856376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984715,0.00006468076,0.00051429,0.0003547679,0.00046041448,0.00013434296],"domain_scores_gemma":[0.9949684,0.002855413,0.00040828792,0.0009821904,0.00072566024,0.00006004334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009280631,0.00011065263,0.0002684214,0.00006739289,0.00018681753,0.000060118844,0.00063442753,0.000030712847,0.000021543492],"category_scores_gemma":[0.0030379454,0.00008480906,0.00003208894,0.0010431411,0.000056100806,0.00017348691,0.00030942843,0.00006193435,0.0000040041523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074504125,0.00028865025,0.0071378453,0.00007081478,0.0012778434,0.0000011148255,0.000059454942,0.21675348,0.0000074130608,0.6569036,0.1112693,0.0061559677],"study_design_scores_gemma":[0.0003560332,0.000012695393,0.02601737,0.0000036055412,0.0013380069,0.000001197017,0.0000102172335,0.66072685,5.641074e-7,0.31117862,0.00028451506,0.000070296126],"about_ca_topic_score_codex":0.001109942,"about_ca_topic_score_gemma":0.00026683905,"teacher_disagreement_score":0.4439734,"about_ca_system_score_codex":0.00003797498,"about_ca_system_score_gemma":0.00010913835,"threshold_uncertainty_score":0.36369237},"labels":[],"label_agreement":null},{"id":"W1912364885","doi":"10.1016/j.csda.2015.10.007","title":"Regularized quantile regression under heterogeneous sparsity with application to quantitative genetic traits","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Quantile regression; Quantile; Regression; Regression analysis; Computer science; Econometrics; Statistics; Mathematics; Machine learning","score_opus":0.18293511268117113,"score_gpt":0.4206050585562977,"score_spread":0.23766994587512658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1912364885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015959166,0.000036469395,0.97908014,0.00015779506,0.00003113783,0.0003273268,0.004288595,0.000058163114,0.000061211635],"genre_scores_gemma":[0.18471509,0.0000034155507,0.8127621,0.00013661012,0.000026608917,0.000022323095,0.0022713586,0.000023340646,0.000039200433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997197,0.00033449827,0.00055081316,0.0007582086,0.0008791857,0.00028032516],"domain_scores_gemma":[0.99573785,0.0020313035,0.00031183253,0.00075040903,0.0007937945,0.00037482145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006411815,0.0002617792,0.0005666204,0.00027295307,0.00016576817,0.00011379502,0.0005206835,0.00006893498,0.000095091375],"category_scores_gemma":[0.0015843282,0.00021381247,0.000051178875,0.0012584322,0.00012763216,0.00009896244,0.0002501145,0.00013107472,0.000074965516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039927886,0.00041043846,0.0023524538,0.00006726683,0.0016738931,0.000048222537,0.000497324,0.2724338,0.000066592045,0.6912619,0.010331224,0.020457644],"study_design_scores_gemma":[0.00035030072,0.00013177702,0.018098949,0.00001607828,0.0010199897,0.000006927129,0.000049394617,0.58310825,0.000009275222,0.39681074,0.00016269056,0.00023560385],"about_ca_topic_score_codex":0.00025169196,"about_ca_topic_score_gemma":0.00047078516,"teacher_disagreement_score":0.3106745,"about_ca_system_score_codex":0.0000889135,"about_ca_system_score_gemma":0.00017839299,"threshold_uncertainty_score":0.8719019},"labels":[],"label_agreement":null},{"id":"W1927455312","doi":"10.1016/j.csda.2015.10.008","title":"Clustering, classification, discriminant analysis, and dimension reduction via generalized hyperbolic mixtures","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear discriminant analysis; Mathematics; Dimensionality reduction; Cluster analysis; Discriminant; Pattern recognition (psychology); Dimension (graph theory); Optimal discriminant analysis; Reduction (mathematics); Artificial intelligence; Statistics; Combinatorics; Computer science; Geometry","score_opus":0.0754486668289481,"score_gpt":0.3390932652654944,"score_spread":0.2636445984365463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1927455312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015486905,0.00038863797,0.99675894,0.00050231005,0.00015422842,0.00011067991,0.00043404926,0.000065980006,0.000036482423],"genre_scores_gemma":[0.22602437,0.00006892631,0.76893437,0.00011300245,0.0000643599,0.000006912036,0.004714383,0.000009002503,0.000064699896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973512,0.0003559842,0.000521234,0.0009440906,0.000585854,0.00024159513],"domain_scores_gemma":[0.9976725,0.00014755968,0.00029032008,0.001181228,0.0004276543,0.00028076363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086153037,0.000227387,0.00048819694,0.0006759506,0.00022557878,0.00032616704,0.0007387299,0.000073194286,0.000011856934],"category_scores_gemma":[0.00011932305,0.00020383277,0.00009331709,0.002336661,0.00010383829,0.0005105096,0.00060544914,0.00011955634,0.000007967352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008585783,0.00047957417,0.009227887,0.000066834,0.011180832,0.000055576547,0.0025386892,0.20646195,0.0012428329,0.36725673,0.02740455,0.37399867],"study_design_scores_gemma":[0.00023613537,0.000021360009,0.038969234,0.000002622189,0.0029207894,0.000014343056,0.000008073602,0.89177203,0.000013090028,0.06544658,0.000368914,0.00022684074],"about_ca_topic_score_codex":0.00070156145,"about_ca_topic_score_gemma":0.00022070885,"teacher_disagreement_score":0.68531007,"about_ca_system_score_codex":0.000058844915,"about_ca_system_score_gemma":0.00010597518,"threshold_uncertainty_score":0.8312059},"labels":[],"label_agreement":null},{"id":"W1934322450","doi":"10.1016/j.csda.2014.12.005","title":"A Bayesian non-parametric approach to asymmetric dynamic conditional correlation model with application to portfolio selection","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministerio de Economía y Competitividad; Mountain Equipment Co-operative","keywords":"Selection (genetic algorithm); Portfolio; Bayesian probability; Parametric statistics; Computer science; Econometrics; Semiparametric model; Model selection; Machine learning; Mathematics; Artificial intelligence; Statistics; Economics; Financial economics","score_opus":0.019096434473422175,"score_gpt":0.25620190830502765,"score_spread":0.23710547383160546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1934322450","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040592984,0.000023036013,0.9892085,0.0000818568,0.000033214103,0.00041237616,0.005211399,0.000042035084,0.0009282573],"genre_scores_gemma":[0.5695018,0.0000035709472,0.4155225,0.00015226855,0.000028699695,0.00004313436,0.0146622965,0.00001710131,0.00006860464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976421,0.000027157741,0.00078482734,0.0010189721,0.0002400258,0.00028688894],"domain_scores_gemma":[0.99832857,0.00020917098,0.0003955515,0.0005519706,0.00030320548,0.0002115306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007801956,0.0002242659,0.00050897925,0.002185452,0.0002748106,0.00014722152,0.00038893818,0.00009116573,0.000026012414],"category_scores_gemma":[0.0004015668,0.00026746487,0.000070162714,0.005738374,0.000029954905,0.0003105756,0.000114970295,0.00016349474,0.00019239655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025262221,0.000121131445,0.022248004,0.000012152417,0.00017841598,1.3991632e-7,0.000047773738,0.85577434,4.1946262e-7,0.11722558,0.0009363964,0.003430372],"study_design_scores_gemma":[0.00021427587,0.000056614845,0.12381989,0.0000027782005,0.00018344294,0.0000011942703,0.0000041225007,0.8099166,1.7860211e-7,0.06518907,0.00034696236,0.00026488715],"about_ca_topic_score_codex":0.0007099435,"about_ca_topic_score_gemma":0.00022134624,"teacher_disagreement_score":0.573686,"about_ca_system_score_codex":0.0002368728,"about_ca_system_score_gemma":0.00007949089,"threshold_uncertainty_score":0.99997777},"labels":[],"label_agreement":null},{"id":"W1940434104","doi":"10.1016/j.csda.2014.07.004","title":"Horizon effect in the term structure of long-run risk-return trade-offs","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université du Québec à Montréal","funders":"","keywords":"Term (time); Economics; Horizon; Business; Monetary economics; Econometrics; Financial economics; Mathematics","score_opus":0.023341312847722864,"score_gpt":0.2611931828418193,"score_spread":0.23785186999409644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940434104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3232474,0.00020862861,0.6657414,0.00005764686,0.00005548735,0.00008852823,0.010547049,0.0000055382948,0.00004836246],"genre_scores_gemma":[0.9735999,0.000052689422,0.020089462,0.000047303536,0.00007011418,0.0000021719686,0.006123901,0.000010338481,0.0000040961922],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836427,0.00013547356,0.0007335549,0.00045522628,0.00012924925,0.00018224922],"domain_scores_gemma":[0.99786514,0.00091007096,0.0004987319,0.00065310305,0.000035325927,0.000037608796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011488325,0.00015320428,0.0005306874,0.00032768855,0.00011920783,0.00006978004,0.00061079237,0.000074028685,0.000075601165],"category_scores_gemma":[0.0006556474,0.00013699377,0.000100829755,0.0008274819,0.00007116278,0.00014360066,0.00009344349,0.00022800831,0.000011196034],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001992273,0.000052547504,0.85881054,0.000042532814,0.00027296998,0.0000021416352,0.00031013312,0.07900306,0.0000011694316,0.042380676,0.0004905499,0.018613743],"study_design_scores_gemma":[0.0001601834,0.000042815354,0.45240548,0.000003345745,0.00013702187,2.4554308e-7,0.0000028658376,0.48650724,9.924034e-7,0.06052937,0.00013032557,0.0000800995],"about_ca_topic_score_codex":0.0013825091,"about_ca_topic_score_gemma":0.001495722,"teacher_disagreement_score":0.65035254,"about_ca_system_score_codex":0.00003595262,"about_ca_system_score_gemma":0.000021123258,"threshold_uncertainty_score":0.55864435},"labels":[],"label_agreement":null},{"id":"W1964670877","doi":"10.1016/j.csda.2008.02.034","title":"A random effects four-part model, with application to correlated medical costs","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Virginia; Agency for Healthcare Research and Quality; Ryerson University","keywords":"Random effects model; Mathematics; Statistics; Laplace's method; Applied mathematics; Generalized estimating equation; Mixed model; Generalized linear model; Generalized linear mixed model; Multivariate statistics; Linear model; Laplace transform; Econometrics; Medicine; Mathematical analysis","score_opus":0.06068986729945356,"score_gpt":0.3676426477605897,"score_spread":0.3069527804611361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964670877","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009425684,0.000014157833,0.9951265,0.00020673047,0.000039074293,0.00041729966,0.00299358,0.000080032994,0.00018006538],"genre_scores_gemma":[0.07414556,0.00001726285,0.9212666,0.00029178557,0.000053016418,0.00006610318,0.004077234,0.000026700322,0.000055727443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969023,0.00024626194,0.0006024285,0.00068084226,0.0012682958,0.00029987455],"domain_scores_gemma":[0.99190944,0.006226509,0.00021986508,0.00077629235,0.00044680017,0.00042108996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006740235,0.00025119277,0.00064935815,0.0002469936,0.00026813083,0.000054401702,0.0005736261,0.00009976169,0.0002234117],"category_scores_gemma":[0.004109351,0.00020945369,0.000057025747,0.0012988055,0.00017463499,0.00010774673,0.00021966205,0.00022527558,0.00008020917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050973834,0.00060111727,0.0048642694,0.00016996382,0.0030891413,0.00043439996,0.00031722625,0.09580404,0.000006763926,0.75270635,0.0722169,0.069280095],"study_design_scores_gemma":[0.000843377,0.0000584397,0.0030600505,0.000034579498,0.0011609787,0.000027530377,0.0000027730823,0.8156425,0.00000177965,0.17878453,0.00015148541,0.00023197556],"about_ca_topic_score_codex":0.00015365504,"about_ca_topic_score_gemma":0.00023632126,"teacher_disagreement_score":0.71983844,"about_ca_system_score_codex":0.0000858697,"about_ca_system_score_gemma":0.00028342707,"threshold_uncertainty_score":0.8541274},"labels":[],"label_agreement":null},{"id":"W1964675414","doi":"10.1016/j.csda.2011.12.001","title":"Corrigendum to “Robust smoothing of gridded data in one and higher dimensions with missing values” [Comput. Statist. Data Anal. 54 (2010) 1167–1178]","year":2011,"lang":"en","type":"erratum","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Missing data; Smoothing; Mathematics; Statistics; Applied mathematics; Econometrics","score_opus":0.3844333747384021,"score_gpt":0.3970219228049661,"score_spread":0.01258854806656401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964675414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004311118,0.0003883661,0.82447624,0.00013525027,0.0016425032,0.00041687107,0.17250447,0.00004322519,0.00034994486],"genre_scores_gemma":[0.0002690698,0.0002194075,0.8213018,0.00015316304,0.0002304479,0.000008303235,0.17558877,0.00010497696,0.0021240327],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99199164,0.00076008006,0.0020817497,0.002698977,0.0017542149,0.0007133234],"domain_scores_gemma":[0.9858657,0.0049900194,0.0014511555,0.0062952833,0.0008757051,0.00052213593],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025960843,0.00081698963,0.0023398616,0.0011980168,0.00031113217,0.0003149763,0.0038935014,0.0003436175,0.0010560473],"category_scores_gemma":[0.0053707473,0.00076924654,0.00005837297,0.002203615,0.0004840511,0.00052254857,0.0055417893,0.0011448764,0.000016809166],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010727314,0.0005860694,0.0014129416,0.00082281907,0.0036849251,0.00014767247,0.0003336327,0.0011768005,0.0000023467371,0.051621865,0.9220524,0.018051289],"study_design_scores_gemma":[0.0006774163,0.00016445131,0.05248646,0.0008674235,0.008585754,0.000009278674,0.00004781283,0.74307114,5.010536e-7,0.18618406,0.0067778127,0.0011279056],"about_ca_topic_score_codex":0.005970866,"about_ca_topic_score_gemma":0.0037248784,"teacher_disagreement_score":0.91527456,"about_ca_system_score_codex":0.00011795918,"about_ca_system_score_gemma":0.0008895856,"threshold_uncertainty_score":0.9998571},"labels":[],"label_agreement":null},{"id":"W1967397577","doi":"10.1016/j.csda.2007.07.018","title":"ANOVA extensions for mixed discrete and continuous data","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics; Mixed model; Context (archaeology); Multivariate statistics; Statistics; Statistical hypothesis testing; Likelihood-ratio test; Monte Carlo method; Extension (predicate logic); Computer science","score_opus":0.17811625952285656,"score_gpt":0.4531567339927464,"score_spread":0.2750404744698899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967397577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000495536,0.00003432543,0.87317693,0.00037113868,0.00004079659,0.00028547272,0.1254635,0.000059157108,0.000073169795],"genre_scores_gemma":[0.17828557,0.0000084909925,0.6927505,0.00011570063,0.000043709424,0.000011543986,0.1286855,0.000014381326,0.00008459406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798733,0.00004491566,0.0006612185,0.0006708472,0.00037062488,0.00026504314],"domain_scores_gemma":[0.9926598,0.00520473,0.0002545344,0.0012024387,0.00048054673,0.00019796765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010076924,0.00017453003,0.00037377357,0.0001746164,0.000360212,0.00012299525,0.0005736651,0.000056031302,0.00013287306],"category_scores_gemma":[0.0037856638,0.00017191774,0.000041413572,0.000683236,0.00018732375,0.00018938298,0.00046302343,0.00009342367,0.0000108033255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017481112,0.00010596108,0.00038583693,0.000032530905,0.000514245,0.0000040847917,0.000020159725,0.00033421855,0.000005777353,0.9068184,0.07936037,0.012400928],"study_design_scores_gemma":[0.00033961984,0.00001347726,0.035055622,0.0000058796336,0.0016662865,0.00000422403,0.00004056062,0.66258174,0.0000015409286,0.2950865,0.0050241575,0.0001803896],"about_ca_topic_score_codex":0.000058481004,"about_ca_topic_score_gemma":0.00032451772,"teacher_disagreement_score":0.66224754,"about_ca_system_score_codex":0.000028542101,"about_ca_system_score_gemma":0.00005572718,"threshold_uncertainty_score":0.7010602},"labels":[],"label_agreement":null},{"id":"W1968451041","doi":"10.1016/j.csda.2004.11.002","title":"Online EM algorithm for mixture with application to internet traffic modeling","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada); Université de Moncton","funders":"Atlantic Canada Opportunities Agency; Nortel Networks Inc","keywords":"Mixture model; Algorithm; Computer science; Expectation–maximization algorithm; Likelihood function; Bayesian information criterion; The Internet; Internet traffic; Function (biology); Data mining; Bayesian probability; Projection (relational algebra); Bayesian network; Maximum likelihood; Estimation theory; Mathematics; Artificial intelligence; Statistics","score_opus":0.02809426787345406,"score_gpt":0.3187321460669584,"score_spread":0.29063787819350434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968451041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029238066,0.000043415093,0.994761,0.00041537327,0.000040118724,0.00030155384,0.004068326,0.00007456709,0.0000032713685],"genre_scores_gemma":[0.030590601,0.0000040342366,0.95659554,0.0005005065,0.000079845086,0.00003198733,0.012158066,0.000015423218,0.000023980527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817187,0.000042520573,0.00035178446,0.0008170511,0.00038513466,0.00023166348],"domain_scores_gemma":[0.99835885,0.00016439603,0.00012184514,0.0007959512,0.00039617045,0.00016280217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032263045,0.00019130688,0.00030782152,0.00027967733,0.00011633831,0.00022251724,0.0011191264,0.000051186144,0.0000034974807],"category_scores_gemma":[0.000039338986,0.0001705605,0.000060264294,0.0011573494,0.000020234105,0.00027911685,0.00024961363,0.000106842934,0.00000746867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043003256,0.000082181636,0.000003796393,0.000005779437,0.0002286743,0.0000025297604,0.00017145884,0.63394976,7.8267686e-7,0.037232894,0.00023391283,0.32808396],"study_design_scores_gemma":[0.00034482463,0.000064914515,0.00014085199,0.000009423759,0.00036954638,0.0000032524497,0.0000072059415,0.93458176,0.0000019629092,0.06398468,0.00027941138,0.00021216222],"about_ca_topic_score_codex":0.00011247775,"about_ca_topic_score_gemma":0.00055775174,"teacher_disagreement_score":0.3278718,"about_ca_system_score_codex":0.0000687246,"about_ca_system_score_gemma":0.00013949984,"threshold_uncertainty_score":0.6955255},"labels":[],"label_agreement":null},{"id":"W1970176118","doi":"10.1016/j.csda.2010.08.011","title":"Applications of the characteristic function-based continuum GMM in finance","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Grey System Theory Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Autoregressive model; Econometrics; Economics; Risk premium; Generalized method of moments; Moment (physics); Variance (accounting); Mathematics; Statistical physics; Computer science; Physics; Panel data; Classical mechanics","score_opus":0.04664258040655074,"score_gpt":0.36758855310519173,"score_spread":0.320945972698641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970176118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023250803,0.000013269511,0.9666327,0.000389972,0.0001314685,0.00033092144,0.009101755,0.000012105526,0.00013698282],"genre_scores_gemma":[0.95127124,6.3888945e-7,0.045856643,0.000116456424,0.000040781233,0.0000891476,0.0023854317,0.000007978167,0.00023166016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99695456,0.00023685383,0.0010484653,0.00060522323,0.0010014535,0.00015343078],"domain_scores_gemma":[0.99187833,0.0041795867,0.0007871871,0.0022842991,0.0008182518,0.000052334828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00212912,0.0001293214,0.0003640097,0.00046083904,0.0002109355,0.00012496645,0.0019864333,0.000056972578,0.000477315],"category_scores_gemma":[0.0021063075,0.00009872472,0.00009925677,0.0042958497,0.00028428662,0.00014651069,0.00026141448,0.00020708653,0.00015792242],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041201434,0.0004770026,0.42578825,0.000023112289,0.0003647369,0.0000017828077,0.00013504413,0.11137388,0.00039909146,0.4114692,0.013820879,0.036105808],"study_design_scores_gemma":[0.000120459095,0.0000039616716,0.5451292,0.0000027360677,0.0001983955,4.7738115e-7,0.000012999032,0.32975435,0.000005520732,0.11425363,0.010441236,0.00007702959],"about_ca_topic_score_codex":0.00015800742,"about_ca_topic_score_gemma":0.003468347,"teacher_disagreement_score":0.9280205,"about_ca_system_score_codex":0.000021560121,"about_ca_system_score_gemma":0.00024047359,"threshold_uncertainty_score":0.52262646},"labels":[],"label_agreement":null},{"id":"W1970310067","doi":"10.1016/j.csda.2009.11.001","title":"Indices for covariance mis-specification in longitudinal data analysis with no missing responses and with MAR drop-outs","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Missing data; Covariance; Longitudinal data; Drop out; Statistics; Mathematics; Analysis of covariance; Drop (telecommunication); Econometrics; Computer science; Data mining; Economics","score_opus":0.17255435794058965,"score_gpt":0.42876486821435345,"score_spread":0.2562105102737638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970310067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012268343,0.000075732416,0.9819185,0.00033220954,0.000011406338,0.0002584026,0.016090812,0.000026130463,0.000059935555],"genre_scores_gemma":[0.089044176,0.000019424326,0.89745367,0.00006073382,0.000040393057,0.000009478514,0.0133137815,0.000015031304,0.00004328851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719054,0.00024405171,0.00064726983,0.0010566871,0.0005689081,0.00029252],"domain_scores_gemma":[0.9923162,0.005423891,0.00046318604,0.0012184435,0.00043940908,0.00013889269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011816729,0.00026766566,0.00072367623,0.0006087613,0.0002283724,0.00031502603,0.0006585251,0.00006321588,0.000117024334],"category_scores_gemma":[0.0020559016,0.00021892275,0.000035205125,0.0021508138,0.00019213847,0.000368495,0.000108236534,0.00015160683,0.0000036526599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031460174,0.0010853846,0.23298444,0.0004361438,0.011122926,0.00023724424,0.0006208007,0.008682664,0.00003025836,0.5907165,0.0063100727,0.14462759],"study_design_scores_gemma":[0.00044634438,0.000119798075,0.28971738,0.0000388946,0.0047338638,0.0000048838415,0.00002819489,0.5648365,9.783325e-7,0.13968632,0.00014669022,0.00024016068],"about_ca_topic_score_codex":0.00017439385,"about_ca_topic_score_gemma":0.000884662,"teacher_disagreement_score":0.55615383,"about_ca_system_score_codex":0.00005161541,"about_ca_system_score_gemma":0.00016665253,"threshold_uncertainty_score":0.8927411},"labels":[],"label_agreement":null},{"id":"W1972278166","doi":"10.1016/j.csda.2011.09.021","title":"Absolute penalty and shrinkage estimation in partially linear models","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Mathematics; Lasso (programming language); Semiparametric regression; Linear model; Context (archaeology); Semiparametric model; Applied mathematics; Monte Carlo method; Statistics; Mathematical optimization; Computer science","score_opus":0.24439516419015378,"score_gpt":0.40813060974234927,"score_spread":0.1637354455521955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972278166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051992806,0.000026772026,0.9912067,0.000025423853,0.00002642935,0.00015148114,0.002921218,0.000028881419,0.00041380594],"genre_scores_gemma":[0.23014429,0.000021135516,0.7684287,0.000044923672,0.0000124856315,0.000010803232,0.001306262,0.000011356883,0.000020054647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981795,0.00016983888,0.00060681725,0.00046660806,0.00035981616,0.00021739729],"domain_scores_gemma":[0.99740225,0.0016399033,0.00018723236,0.00047148185,0.0001757449,0.00012336335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008275309,0.00016712256,0.0003867578,0.00025765182,0.00008889462,0.000051459258,0.00029393935,0.00005572824,0.00028587648],"category_scores_gemma":[0.0012673348,0.00016194423,0.00003299282,0.00059702527,0.00011040788,0.00023665755,0.00024787855,0.00014484534,0.00001525671],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023615105,0.00016642122,0.0033581129,0.00006164161,0.00037751006,0.000032610693,0.000507752,0.036719866,8.9910566e-7,0.9401933,0.0008052976,0.017752972],"study_design_scores_gemma":[0.00011302918,0.0000143683965,0.034600407,0.0000073687484,0.00032099284,0.0000011040618,0.0000073832243,0.5073972,7.641776e-7,0.4574345,0.000008874252,0.00009403304],"about_ca_topic_score_codex":0.00053216564,"about_ca_topic_score_gemma":0.00073977106,"teacher_disagreement_score":0.4827588,"about_ca_system_score_codex":0.000026756472,"about_ca_system_score_gemma":0.00006691036,"threshold_uncertainty_score":0.6603894},"labels":[],"label_agreement":null},{"id":"W1972856794","doi":"10.1016/j.csda.2011.10.012","title":"Exact nonparametric meta-analysis for multiple independent doubly Type-II censored samples","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Nonparametric statistics; Quantile; Mathematics; Statistics; Order statistic; Confidence interval; CDF-based nonparametric confidence interval; Population; Sample size determination; Coverage probability; Type I and type II errors; Sample (material); Econometrics; Applied mathematics","score_opus":0.4337328912081405,"score_gpt":0.42562144637180815,"score_spread":0.00811144483633236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972856794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044604062,0.00005842775,0.90905327,0.00009752652,0.000033084398,0.00044001796,0.08963874,0.00008913521,0.00014379447],"genre_scores_gemma":[0.42116117,0.000005620047,0.53034014,0.00007289054,0.000016653732,0.00007942939,0.048180625,0.000016614078,0.00012683668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968723,0.00014160399,0.0010391423,0.00085409364,0.00074539677,0.00034744875],"domain_scores_gemma":[0.9922509,0.0045785774,0.0005640647,0.0011849633,0.001179207,0.00024226187],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070737366,0.0003209211,0.0011562124,0.0008364228,0.0005077903,0.00011855784,0.0007263585,0.00010091483,0.0049954774],"category_scores_gemma":[0.003691092,0.00029241716,0.0006498039,0.0044049164,0.00013661271,0.00018765008,0.00027432357,0.00013950316,0.00007649654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057857647,0.000722076,0.0021479828,0.000041009236,0.15822817,0.000003418019,0.0001479693,0.027405841,0.000001952808,0.7967506,0.013873576,0.00061952835],"study_design_scores_gemma":[0.00031933925,0.000032966956,0.03724011,5.7943214e-7,0.23031536,8.622451e-7,0.000020430813,0.5486374,0.00000564266,0.18245268,0.00070838025,0.00026627773],"about_ca_topic_score_codex":0.00045421824,"about_ca_topic_score_gemma":0.0005000632,"teacher_disagreement_score":0.6142979,"about_ca_system_score_codex":0.00007927443,"about_ca_system_score_gemma":0.00010860692,"threshold_uncertainty_score":0.9999528},"labels":[],"label_agreement":null},{"id":"W1972870561","doi":"10.1016/j.csda.2013.10.027","title":"Inference for longitudinal data with nonignorable nonmonotone missing responses","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Missing data; Inference; Monte Carlo method; Computer science; Computation; Generalized estimating equation; Longitudinal data; Statistical inference; Sampling (signal processing); Sample (material); Estimating equations; Statistics; Mathematics; Algorithm; Artificial intelligence; Data mining; Machine learning","score_opus":0.2026380183625323,"score_gpt":0.44893320202063297,"score_spread":0.24629518365810066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972870561","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006011496,0.00003165489,0.9721798,0.00029256984,0.000033939505,0.00040372674,0.026324764,0.000050189232,0.000082260005],"genre_scores_gemma":[0.03946087,0.0000096067,0.94529986,0.00007152016,0.000061963554,0.000047070916,0.014920887,0.000028872842,0.00009933344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972146,0.00020364168,0.0006453083,0.0009725273,0.0005732276,0.00039070778],"domain_scores_gemma":[0.9829697,0.013854855,0.0003437301,0.0018721052,0.0007587591,0.00020086557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095513655,0.00027681282,0.00061560294,0.000245534,0.0003568838,0.0004725639,0.001236162,0.000063756575,0.00077595795],"category_scores_gemma":[0.0063034426,0.00023102965,0.000042714113,0.0008251757,0.00022216834,0.00058934774,0.0005589749,0.00015864562,0.00004244419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028615893,0.0005619293,0.031308547,0.00039659327,0.0038874114,0.000052234296,0.00014591806,0.002846171,0.000024741375,0.7759952,0.051901616,0.13259348],"study_design_scores_gemma":[0.00023832305,0.000055622306,0.01961972,0.000025251606,0.0012831225,0.0000035144094,0.000015487349,0.5325147,0.0000024065316,0.44576502,0.00025992474,0.00021691876],"about_ca_topic_score_codex":0.0006768054,"about_ca_topic_score_gemma":0.00032024985,"teacher_disagreement_score":0.5296685,"about_ca_system_score_codex":0.00004262533,"about_ca_system_score_gemma":0.00030402906,"threshold_uncertainty_score":0.94211155},"labels":[],"label_agreement":null},{"id":"W1973129529","doi":"10.1016/j.csda.2011.07.017","title":"A mixed effects log-linear model based on the Birnbaum–Saunders distribution","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Mathematics; Statistics; Linear regression; Log-linear model; Linear model; Regression analysis; Covariate; Mixed model; Proper linear model; Logarithm; Monte Carlo method; Generalized linear mixed model; Applied mathematics; Bayesian multivariate linear regression","score_opus":0.23276118141286134,"score_gpt":0.3726354927082137,"score_spread":0.13987431129535238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973129529","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004812834,0.000003876569,0.9625241,0.00044998896,0.000036062076,0.00031861843,0.035756387,0.0001005285,0.00032915367],"genre_scores_gemma":[0.55809504,0.0000014100611,0.40594792,0.00034127638,0.000016200185,0.000054182878,0.03549009,0.000014570199,0.000039331564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977982,0.00020495763,0.0005441124,0.000531592,0.00065627723,0.00026485886],"domain_scores_gemma":[0.99419564,0.003971789,0.00027614474,0.0010264069,0.00037438792,0.0001556318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053617085,0.0002403563,0.00032246643,0.00013135548,0.0004392707,0.000069647045,0.0005949593,0.000071408795,0.00045073943],"category_scores_gemma":[0.00256621,0.00019077396,0.00011379911,0.001112107,0.00022867811,0.00009704197,0.00012696315,0.00019353669,0.00016635559],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020824671,0.00031682523,0.0001579486,0.000028454197,0.0003160601,0.0000031108175,0.000030626452,0.07552777,0.0000012532391,0.88374484,0.038936287,0.0009160153],"study_design_scores_gemma":[0.0001879725,0.00001725287,0.008674548,0.00000722898,0.0008571303,3.7429135e-7,0.0000091731745,0.63280654,0.0000087766275,0.3572193,0.0000754082,0.00013627931],"about_ca_topic_score_codex":0.000058301433,"about_ca_topic_score_gemma":0.00003337075,"teacher_disagreement_score":0.55761373,"about_ca_system_score_codex":0.0001031535,"about_ca_system_score_gemma":0.00012090898,"threshold_uncertainty_score":0.7779536},"labels":[],"label_agreement":null},{"id":"W1975134946","doi":"10.1016/j.csda.2014.02.019","title":"Sample size determination for estimating prevalence and a difference between two prevalences of sensitive attributes using the non-randomized triangular design","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Science Foundation of Chongqing","keywords":"Statistics; Sample size determination; Mathematics; Estimation; Contrast (vision); Sample (material); Randomized response; Small area estimation; Computer science; Artificial intelligence; Engineering","score_opus":0.1919506222280558,"score_gpt":0.42107482674447133,"score_spread":0.22912420451641552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975134946","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02038845,0.00002125431,0.9739013,0.00003325871,0.000020686217,0.0006567572,0.0049435175,0.0000339728,8.53272e-7],"genre_scores_gemma":[0.3757926,0.0000054097354,0.62347513,0.000008182603,0.00003315603,0.000022175385,0.0006518749,0.000008126764,0.0000033423203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976202,0.0007986289,0.0007004925,0.00035959858,0.00036941824,0.00015165597],"domain_scores_gemma":[0.8946125,0.10373705,0.0006958537,0.0003590111,0.00055359956,0.000041966898],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005085258,0.00017064821,0.00068699155,0.00013249773,0.0002770813,0.00009120212,0.00029397273,0.000042210497,0.0000076378],"category_scores_gemma":[0.038712185,0.00013103863,0.000084361986,0.0003577713,0.00030031003,0.00012719308,0.00012700708,0.000070011956,1.8287805e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004157528,0.000500889,0.06541961,0.005773541,0.009694454,0.0000031557229,0.007642036,0.5907087,0.00029552192,0.076447465,0.000852583,0.23850451],"study_design_scores_gemma":[0.001954697,0.000025539086,0.005235961,0.00006809394,0.002458474,7.2657576e-7,0.000012481004,0.7129993,0.0000661146,0.2770756,3.1738116e-7,0.00010271925],"about_ca_topic_score_codex":0.0002538193,"about_ca_topic_score_gemma":0.000014745522,"teacher_disagreement_score":0.35540414,"about_ca_system_score_codex":0.000022774128,"about_ca_system_score_gemma":0.000051228402,"threshold_uncertainty_score":0.96938515},"labels":[],"label_agreement":null},{"id":"W1975673958","doi":"10.1016/s0167-9473(02)00060-9","title":"Numerical linear algebra in the integrity theory of the Global Positioning System","year":2002,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Global Positioning System; Diagonal; Linear algebra; Position (finance); Computer science; Projection (relational algebra); Orthographic projection; Fault detection and isolation; Algorithm; Mathematics; Algebra over a field; Applied mathematics; Control theory (sociology); Artificial intelligence; Geometry; Pure mathematics","score_opus":0.3433294229604493,"score_gpt":0.42901205299774725,"score_spread":0.08568263003729792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975673958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010713533,0.00007350363,0.9858392,0.00061603065,0.00018132213,0.0001383843,0.0016689932,0.00000784225,0.0007611743],"genre_scores_gemma":[0.9792541,0.0000010352908,0.019820463,0.0001383899,0.0000362374,0.0000033309598,0.0006985076,0.0000021219332,0.00004579514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99408036,0.0015827643,0.0007727213,0.00042894107,0.0029978668,0.00013735674],"domain_scores_gemma":[0.99497676,0.0029472932,0.0003967858,0.0009667385,0.0006752369,0.000037203707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00943449,0.00009699366,0.00024139733,0.00016841473,0.0002699543,0.00022770185,0.0017798687,0.000034124027,0.000559888],"category_scores_gemma":[0.0047059483,0.00005262862,0.00010562668,0.0040453332,0.00015677184,0.000178875,0.00017733732,0.0001402656,0.00007611426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002370375,0.00018792208,0.15483728,0.000009817431,0.00034050876,0.0000044204885,0.000955341,0.40275982,0.0000018467559,0.40095472,0.02006572,0.019858882],"study_design_scores_gemma":[0.00010094259,0.000006289712,0.17303088,0.00000756192,0.00024093536,0.0000017300082,0.0003601609,0.7487147,5.7287826e-7,0.07737207,0.00011745695,0.000046719273],"about_ca_topic_score_codex":0.00021876347,"about_ca_topic_score_gemma":0.0002474235,"teacher_disagreement_score":0.9685406,"about_ca_system_score_codex":0.00010129828,"about_ca_system_score_gemma":0.00006895993,"threshold_uncertainty_score":0.6130381},"labels":[],"label_agreement":null},{"id":"W1975698992","doi":"10.1016/j.csda.2006.08.029","title":"k-Sample tests based on the likelihood ratio","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Sample (material); Sample size determination; Anderson–Darling test; Statistical hypothesis testing; Likelihood-ratio test; Kolmogorov–Smirnov test; Physics","score_opus":0.030429337236413105,"score_gpt":0.2991661943393945,"score_spread":0.2687368571029814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975698992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002991475,0.000028481747,0.99441034,0.0017630862,0.00006753245,0.00010627061,0.0031720754,0.000059436225,0.00036288798],"genre_scores_gemma":[0.12155051,0.0000014763925,0.8723438,0.0012012892,0.0000794322,0.000008746065,0.0047692736,0.0000081450125,0.000037351496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979269,0.00026604978,0.00034849206,0.000601265,0.00061400863,0.00024327352],"domain_scores_gemma":[0.99473536,0.003413644,0.0001646847,0.0013948535,0.0002181993,0.00007325631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007926304,0.00017167444,0.00022794491,0.0002138109,0.0003165416,0.0003993203,0.0014368391,0.000037977017,0.00009329046],"category_scores_gemma":[0.00034287688,0.00012749324,0.00007861689,0.0013865537,0.00006118184,0.00020936552,0.00026807873,0.00013402327,0.000039993705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024444764,0.00009332624,0.0007530642,0.000003377307,0.00012606451,0.000007910588,0.000013619432,0.14707834,0.000003352798,0.80690587,0.02765089,0.017361742],"study_design_scores_gemma":[0.00008518413,0.000014133175,0.014642173,0.0000022834952,0.0001471731,4.441981e-7,4.793978e-7,0.661788,0.0000033798065,0.32235983,0.00085036625,0.000106533604],"about_ca_topic_score_codex":0.00062891544,"about_ca_topic_score_gemma":0.00023192773,"teacher_disagreement_score":0.5147097,"about_ca_system_score_codex":0.000034196335,"about_ca_system_score_gemma":0.00016588188,"threshold_uncertainty_score":0.51990235},"labels":[],"label_agreement":null},{"id":"W1975760434","doi":"10.1016/j.csda.2005.01.011","title":"On some predictors of times to failure of censored items in progressively censored samples","year":2005,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Statistics; Consistency (knowledge bases); Best linear unbiased prediction; Population; Mean squared error; Econometrics; Computer science; Artificial intelligence; Selection (genetic algorithm); Demography","score_opus":0.058318495983690266,"score_gpt":0.3752152618189118,"score_spread":0.3168967658352215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975760434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020151744,0.000012947253,0.9170163,0.0005292654,0.0000137763955,0.0002973801,0.061898444,0.000027883518,0.00005224952],"genre_scores_gemma":[0.5384794,0.000002633309,0.4495992,0.000044822787,0.000017134254,0.000018726454,0.011803235,0.000009433846,0.0000254224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978071,0.000092439615,0.0009143352,0.0003904318,0.0006072388,0.00018846651],"domain_scores_gemma":[0.99627084,0.0022262372,0.00041939688,0.0005307902,0.0004246085,0.00012813482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002548225,0.00016881178,0.00048746864,0.00043746555,0.000060947692,0.00002626815,0.0004003345,0.000056579433,0.00042316614],"category_scores_gemma":[0.002271615,0.00016590994,0.00006643295,0.0011924296,0.00013789147,0.000119124,0.000112990776,0.000095159856,0.00003176101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028970173,0.00043348948,0.0024348432,0.000050625862,0.00034666643,0.0000011746681,0.00012264834,0.07349805,0.000021242424,0.8988313,0.022557259,0.0016736988],"study_design_scores_gemma":[0.0005424618,0.00006167233,0.1406449,0.000052789896,0.00066427427,6.6408e-7,0.00004937175,0.54605764,0.00008304755,0.31092787,0.0006928011,0.00022251815],"about_ca_topic_score_codex":0.0000611584,"about_ca_topic_score_gemma":0.00014009101,"teacher_disagreement_score":0.58790344,"about_ca_system_score_codex":0.000065173255,"about_ca_system_score_gemma":0.000084683576,"threshold_uncertainty_score":0.6765611},"labels":[],"label_agreement":null},{"id":"W1976004269","doi":"10.1016/j.csda.2012.09.005","title":"A consistent method of estimation for the three-parameter Weibull distribution","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":65,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Ministry of Education, Culture, Sports, Science and Technology; McMaster University","keywords":"Weibull distribution; Estimator; Consistency (knowledge bases); Mathematics; Monte Carlo method; Mean squared error; Estimation theory; Parameter space; Applied mathematics; Statistics; Transformation (genetics); Maximum likelihood; Distribution (mathematics); Mathematical optimization; Algorithm; Mathematical analysis","score_opus":0.1756241784525026,"score_gpt":0.4482711406332486,"score_spread":0.27264696218074597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976004269","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012266412,0.000054572865,0.93285495,0.00044625087,0.0000589441,0.00046595672,0.065942064,0.000034435143,0.000020159803],"genre_scores_gemma":[0.24037462,0.0000038423314,0.716255,0.000055175038,0.00003508557,0.00009493089,0.04315216,0.000010061696,0.00001911409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981658,0.00010687342,0.0007286567,0.00028748543,0.00046423567,0.0002469923],"domain_scores_gemma":[0.98608565,0.012068673,0.000461421,0.0006894032,0.0005795339,0.000115315735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011093316,0.00016512601,0.00035584834,0.00008599204,0.00029711574,0.000058171863,0.00036553398,0.000056345783,0.0002658153],"category_scores_gemma":[0.004284865,0.00013059587,0.00013361865,0.0007592577,0.00016509388,0.00016960464,0.00012440688,0.00009017836,0.00002114749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016767735,0.00020832532,0.00074067526,0.000053176445,0.00088122045,9.337551e-8,0.00003717864,0.018202247,0.0000023225987,0.9425486,0.021125354,0.016184082],"study_design_scores_gemma":[0.00018772611,0.000010946107,0.028811079,0.0000046303767,0.0028202212,0.000002061434,0.000014057663,0.69817007,0.00000747152,0.26857606,0.0012930407,0.000102622944],"about_ca_topic_score_codex":0.00007529978,"about_ca_topic_score_gemma":0.000043075263,"teacher_disagreement_score":0.6799678,"about_ca_system_score_codex":0.0000684211,"about_ca_system_score_gemma":0.000067345485,"threshold_uncertainty_score":0.5325545},"labels":[],"label_agreement":null},{"id":"W1976374470","doi":"10.1016/j.csda.2011.10.013","title":"Correlated destructive generalized power series cure rate models and associated inference with an application to a cutaneous melanoma data","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Series (stratigraphy); Mathematics; Overdispersion; Inference; Statistics; Applied mathematics; Distribution (mathematics); Interpretation (philosophy); Algorithm; Computer science; Biological system; Artificial intelligence; Biology; Count data; Mathematical analysis","score_opus":0.12468577322492502,"score_gpt":0.3687864105488416,"score_spread":0.24410063732391657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976374470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009081386,0.0000070249926,0.937077,0.000106661304,0.0000119983315,0.00037345884,0.05309349,0.00010458524,0.0001443888],"genre_scores_gemma":[0.43810338,0.0000070785377,0.4985885,0.0000892904,0.000005916909,0.00003534877,0.06311728,0.000017191884,0.000036006728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978733,0.00017986348,0.0005242273,0.0008142728,0.0003836577,0.00022466663],"domain_scores_gemma":[0.99652797,0.0009412463,0.00033445877,0.0012116843,0.00071929384,0.0002653197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030833978,0.00024507788,0.000400283,0.00017202529,0.0002879434,0.00013478922,0.0006585234,0.00008018565,0.00023588535],"category_scores_gemma":[0.0010066117,0.00022997217,0.000018755833,0.0011111235,0.00017274139,0.00060486636,0.00034639295,0.00013676695,0.000023561232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013553177,0.0002809088,0.0011591351,0.000013907925,0.0009798433,0.000013808996,0.00041732058,0.019411111,0.0000062708777,0.97352755,0.002104157,0.0019504507],"study_design_scores_gemma":[0.00023459063,0.0000706098,0.016221061,0.0000068583463,0.001043456,0.000010860467,0.00004712865,0.6712773,0.0000014318174,0.31081897,0.000057427853,0.00021033686],"about_ca_topic_score_codex":0.0003064665,"about_ca_topic_score_gemma":0.00089346414,"teacher_disagreement_score":0.6627086,"about_ca_system_score_codex":0.000059016373,"about_ca_system_score_gemma":0.00012659046,"threshold_uncertainty_score":0.9377993},"labels":[],"label_agreement":null},{"id":"W1977740308","doi":"10.1016/j.csda.2008.07.032","title":"On empirical Bayes penalized quasi-likelihood inference in GLMMs and in Bayesian disease mapping and ecological modeling","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Child and Family Research Institute","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Ministry of Health, British Columbia; Michael Smith Health Research BC; Child and Family Research Institute","keywords":"Random effects model; Bayes' theorem; Statistics; Generalized linear mixed model; Bayesian probability; Bayesian inference; Context (archaeology); Prediction interval; Mathematics; Econometrics; Point estimation; Bayesian hierarchical modeling; Bayesian linear regression; Credible interval; Geography; Medicine","score_opus":0.16845305648082928,"score_gpt":0.42047765753257565,"score_spread":0.2520246010517464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977740308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10110248,0.000057469642,0.8969304,0.00022001847,0.000015212071,0.00015537944,0.0014730874,0.00002092685,0.000025028514],"genre_scores_gemma":[0.51768845,0.00006777039,0.4816239,0.00008739195,0.000010017896,0.000009902698,0.0005031411,0.00000770262,0.0000017663349],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973156,0.00040798247,0.00074844086,0.00075587415,0.000440052,0.0003320743],"domain_scores_gemma":[0.9908272,0.0082909195,0.0001374012,0.0003683884,0.00010561401,0.00027050092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070200063,0.00024888304,0.0006486614,0.00048632,0.00015813514,0.000088119166,0.00025641013,0.000080497375,0.00012861587],"category_scores_gemma":[0.0069082067,0.00022672158,0.000038432256,0.0008107596,0.00018812095,0.00014937732,0.00029414476,0.0002821833,0.000003680052],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031228331,0.0014734261,0.48645172,0.00026004415,0.0004202961,0.0008783305,0.00094027736,0.031152194,0.000002071495,0.4588398,0.0005788992,0.018690633],"study_design_scores_gemma":[0.00027828885,0.000021809981,0.1436097,0.00002562847,0.0000928289,0.000001869327,0.000016113212,0.453441,2.7442917e-8,0.4023867,0.0000021282558,0.00012393325],"about_ca_topic_score_codex":0.00017688969,"about_ca_topic_score_gemma":0.0005903129,"teacher_disagreement_score":0.42228878,"about_ca_system_score_codex":0.000061508945,"about_ca_system_score_gemma":0.00014197924,"threshold_uncertainty_score":0.92454374},"labels":[],"label_agreement":null},{"id":"W1977809099","doi":"10.1016/j.csda.2013.11.002","title":"Asymptotic distributions for quasi-efficient estimators in echelon VARMA models","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Chrysler (Canada); University of Windsor; McGill University","funders":"","keywords":"Mathematics; Estimator; Applied mathematics; Autoregressive model; Efficient estimator; Mean squared error; Ordinary least squares; Minimum-variance unbiased estimator; Statistics; Consistent estimator; Minimum mean square error; Covariance","score_opus":0.18325253907999733,"score_gpt":0.45071741869636567,"score_spread":0.26746487961636833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977809099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015527173,0.000030086407,0.97546196,0.00012930237,0.000055114393,0.0005749263,0.022098659,0.000050049042,0.000047200974],"genre_scores_gemma":[0.20203073,0.000004792763,0.78776383,0.00003886408,0.000021941363,0.0001191889,0.009962527,0.000022735594,0.000035365087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755645,0.00014827862,0.00079948193,0.00065284193,0.00043544546,0.0004074806],"domain_scores_gemma":[0.9931008,0.0053769336,0.00023579555,0.0006487949,0.0004516279,0.0001860386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006269795,0.00024479316,0.00056590256,0.0002947146,0.0001999328,0.0001089033,0.00043534502,0.000073196665,0.0001566403],"category_scores_gemma":[0.0023262557,0.00023844327,0.00009901638,0.00086674135,0.000108378495,0.00023808565,0.00021389469,0.00015438559,0.000023546183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061004957,0.0002625472,0.00014945299,0.00004376149,0.00021405536,0.000002452249,0.00004271037,0.4795621,0.0000010567936,0.5125899,0.0018283259,0.0052975905],"study_design_scores_gemma":[0.00019927115,0.000018207262,0.0012393467,0.000009648258,0.00042806607,5.539903e-7,0.000012459969,0.5110308,5.7489746e-7,0.48689416,0.00002790718,0.00013898454],"about_ca_topic_score_codex":0.00024353364,"about_ca_topic_score_gemma":0.00010933251,"teacher_disagreement_score":0.20047802,"about_ca_system_score_codex":0.0001401641,"about_ca_system_score_gemma":0.00010809472,"threshold_uncertainty_score":0.97234344},"labels":[],"label_agreement":null},{"id":"W1978245797","doi":"10.1016/j.csda.2009.08.012","title":"Estimating smooth distribution function in the presence of heteroscedastic measurement errors","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Case Western Reserve University","keywords":"Pointwise; Estimator; Heteroscedasticity; Mathematics; Deconvolution; Extrapolation; Statistics; Applied mathematics; Sampling distribution; Mathematical analysis","score_opus":0.17287471248049655,"score_gpt":0.4009278218417641,"score_spread":0.22805310936126758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978245797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004210163,0.000024405052,0.9928839,0.00011367968,0.00005639245,0.00015364624,0.0025063253,0.00002203961,0.000029414301],"genre_scores_gemma":[0.52697647,0.000001280572,0.47170138,0.00003648893,0.00001705442,0.0000038171956,0.0012587624,0.0000039471943,8.127587e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746966,0.00036348004,0.00065943785,0.0003368509,0.0009851767,0.000185386],"domain_scores_gemma":[0.99608743,0.002639323,0.00031838447,0.0005335893,0.0003751154,0.000046158184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019467777,0.00014207674,0.0003252204,0.00012407055,0.00008947503,0.00005932843,0.00044037375,0.0000361124,0.000037482023],"category_scores_gemma":[0.007600685,0.000110091554,0.00004979066,0.001007899,0.00008363359,0.00010472564,0.00006709131,0.0001453713,0.0000022401887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068119545,0.0006329751,0.005900473,0.00013456975,0.00042886607,0.000010974574,0.00035917145,0.2059332,0.00004075549,0.71467,0.0053098267,0.06651107],"study_design_scores_gemma":[0.0000938966,0.000052097817,0.13666502,0.000020962765,0.0004561216,5.074191e-7,0.000016781329,0.51989484,9.708815e-7,0.34271863,0.000015767833,0.000064412234],"about_ca_topic_score_codex":0.00012432314,"about_ca_topic_score_gemma":0.00009970537,"teacher_disagreement_score":0.5227663,"about_ca_system_score_codex":0.00006133189,"about_ca_system_score_gemma":0.00006346,"threshold_uncertainty_score":0.9099279},"labels":[],"label_agreement":null},{"id":"W1978682325","doi":"10.1016/j.csda.2014.06.005","title":"A Bayesian approach to estimating animal density from binary acoustic transects","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Bayesian probability; Mathematics; Statistics; Transect; Poisson distribution; Range (aeronautics); Hidden Markov model; Computer science; Artificial intelligence; Biology; Ecology","score_opus":0.028258791858874418,"score_gpt":0.2716580859343406,"score_spread":0.24339929407546618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978682325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04765572,0.000013230378,0.94931674,0.00007779989,0.0000311979,0.00014020635,0.0018172143,0.00004176799,0.00090610696],"genre_scores_gemma":[0.5164899,0.0000016759263,0.47984964,0.00028199647,0.00004287342,0.000005271941,0.0033075516,0.000009656291,0.000011391542],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770594,0.00013865567,0.00037943092,0.00084344187,0.00064453634,0.00028797548],"domain_scores_gemma":[0.9985141,0.0005312779,0.0001288494,0.0005827023,0.00003575318,0.0002072926],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039566308,0.0002190422,0.0004033291,0.00008104029,0.00031553087,0.000091497954,0.0006391416,0.000038481674,0.00092233723],"category_scores_gemma":[0.00036770792,0.00022364789,0.000065319975,0.0009934714,0.00010000404,0.00017205687,0.0010324438,0.00012040218,0.0002689816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026205707,0.00015696503,0.062586665,0.00002254272,0.00048425322,0.000009399922,0.0001947017,0.9116458,0.00004346095,0.00054717035,0.01112562,0.013157177],"study_design_scores_gemma":[0.00008642592,0.000032622647,0.39173505,0.0000029880653,0.00064530055,8.2104765e-7,0.000007785293,0.60523134,4.3866672e-7,0.001789317,0.00031226195,0.00015565331],"about_ca_topic_score_codex":0.009386188,"about_ca_topic_score_gemma":0.004453981,"teacher_disagreement_score":0.4694671,"about_ca_system_score_codex":0.00010890972,"about_ca_system_score_gemma":0.00001510058,"threshold_uncertainty_score":0.99999094},"labels":[],"label_agreement":null},{"id":"W1979736402","doi":"10.1016/j.csda.2015.04.001","title":"Robust and efficient estimation of effective dose","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Alberta","funders":"Humanities and Social Science Fund of Ministry of Education of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; Nonparametric statistics; Parametric statistics; Robustness (evolution); Asymptotic distribution; Mathematics; Monte Carlo method; Semiparametric model; Parametric model; Context (archaeology); Semiparametric regression; Robust statistics; Sample size determination; Statistics; Econometrics; Computer science","score_opus":0.266889376336155,"score_gpt":0.4777968272809065,"score_spread":0.2109074509447515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979736402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02437102,0.0001494869,0.97289205,0.00003661604,0.000065889755,0.00015738174,0.0021485898,0.000011320959,0.00016767455],"genre_scores_gemma":[0.43756956,0.0000010820398,0.56146604,0.000016602697,0.00000822504,0.0000031396169,0.0009125301,0.0000039190263,0.000018910323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967082,0.0005246803,0.0006163049,0.00055422494,0.0014760947,0.00012050951],"domain_scores_gemma":[0.99408394,0.004105168,0.0003578694,0.0006088023,0.0006775903,0.00016662595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037583392,0.0001233866,0.0003965088,0.00048438407,0.000078865196,0.0001610167,0.0005102126,0.00003492702,0.00008299944],"category_scores_gemma":[0.005941482,0.0001034719,0.0000451722,0.0017599264,0.00020539833,0.00021308575,0.00044522452,0.000063323416,0.000042931097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035384437,0.00007114694,0.002196849,0.0000031776926,0.00019883044,0.000003407404,0.00023334814,0.9424308,0.000012806942,0.007773932,0.0018433403,0.045197006],"study_design_scores_gemma":[0.00028859323,0.00005855289,0.06366749,0.000002875841,0.00033767772,0.000001993059,0.00009540806,0.9000221,0.000023950219,0.03536003,0.000047681802,0.00009364975],"about_ca_topic_score_codex":0.00018201178,"about_ca_topic_score_gemma":0.0000150557635,"teacher_disagreement_score":0.41319853,"about_ca_system_score_codex":0.000051460553,"about_ca_system_score_gemma":0.00009201911,"threshold_uncertainty_score":0.71129376},"labels":[],"label_agreement":null},{"id":"W1980169397","doi":"10.1016/j.csda.2008.07.003","title":"Polynomial spline estimation of partially linear single-index proportional hazards regression models","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Cancer Foundation","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Mathematics; Statistics; Proportional hazards model; Estimator; Nonparametric statistics; Spline (mechanical); Linear model; Nonparametric regression; Polynomial regression; Smoothing; Monte Carlo method; Linear regression","score_opus":0.17312802903297214,"score_gpt":0.4079542573086046,"score_spread":0.23482622827563243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980169397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011266502,0.000026386455,0.98076427,0.000083384206,0.00007194682,0.00016134458,0.0074694795,0.0000434865,0.000113185546],"genre_scores_gemma":[0.39910528,0.000009599718,0.5956237,0.000021912589,0.00006381648,0.00000507477,0.005109642,0.000014230709,0.000046740326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683326,0.00019201824,0.0011229287,0.00053277006,0.001077846,0.00024114414],"domain_scores_gemma":[0.9959339,0.0018689322,0.00065672566,0.0006593477,0.00072856684,0.00015251774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065327255,0.00023855704,0.0006245533,0.00031054934,0.0002158496,0.000030483921,0.00041119268,0.00009581745,0.0003592032],"category_scores_gemma":[0.0026985626,0.0002107919,0.0001081932,0.00082313776,0.00027965932,0.00024002648,0.00024510347,0.00016666242,0.000010932689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014739117,0.0007097955,0.0031827788,0.00011708369,0.0009312698,0.000041242594,0.00015817229,0.84575886,0.000031841893,0.10905409,0.015903754,0.023963757],"study_design_scores_gemma":[0.00029067197,0.000060799324,0.008650321,0.000025795933,0.0006773814,0.000008808935,0.000004777522,0.783139,0.000028824685,0.20689054,0.000047112328,0.0001759518],"about_ca_topic_score_codex":0.0001659383,"about_ca_topic_score_gemma":0.00005497035,"teacher_disagreement_score":0.38783878,"about_ca_system_score_codex":0.000060558847,"about_ca_system_score_gemma":0.00034951858,"threshold_uncertainty_score":0.8595844},"labels":[],"label_agreement":null},{"id":"W1980933469","doi":"10.1016/j.csda.2010.01.031","title":"Fast robust estimation of prediction error based on resampling","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Vlaamse regering; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Resampling; Estimator; Trimming; Robustness (evolution); Robust regression; Linear regression; Mathematics; Statistics; Mean squared prediction error; Robust statistics; Errors-in-variables models; Regression; Linear model; Mean squared error; Observational error; Computer science; Algorithm","score_opus":0.17583020892952297,"score_gpt":0.44692977556854113,"score_spread":0.27109956663901813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980933469","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012758855,0.0000023673022,0.9746137,0.000054251792,0.00010823572,0.00014403906,0.023631254,0.00004505871,0.00012520848],"genre_scores_gemma":[0.18138848,0.000001041143,0.80813617,0.000034398596,0.00003986431,0.0000075976554,0.0103540765,0.000017699233,0.000020679472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799263,0.00010886802,0.0006397213,0.00046925197,0.0006140552,0.00017548254],"domain_scores_gemma":[0.9944232,0.0040014386,0.0003620809,0.0007552676,0.000351928,0.0001060656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007540898,0.00017064238,0.00038834434,0.0003096717,0.000151148,0.000040432395,0.00030238464,0.00007411363,0.00022019481],"category_scores_gemma":[0.003783695,0.00016515992,0.00006798947,0.0006029811,0.00011738783,0.0001475437,0.00008937065,0.0002448167,0.0000061086575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027244945,0.00012964034,0.0002858467,0.000046212685,0.00016625879,0.0000020936109,0.000023809507,0.77710235,0.00001879032,0.20735247,0.0007148975,0.014130406],"study_design_scores_gemma":[0.00018309482,0.00003333258,0.0035613852,0.000012369666,0.0006801105,4.875479e-7,0.0000053976023,0.6703776,0.0000074891864,0.32500976,0.000035013985,0.000093949755],"about_ca_topic_score_codex":0.00004468252,"about_ca_topic_score_gemma":0.0000947826,"teacher_disagreement_score":0.18011259,"about_ca_system_score_codex":0.000027789021,"about_ca_system_score_gemma":0.00008494032,"threshold_uncertainty_score":0.6735026},"labels":[],"label_agreement":null},{"id":"W1982580511","doi":"10.1016/j.csda.2010.06.003","title":"Estimation from aggregate data","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Aggregate (composite); Data set; Estimation; Aggregate data; Reliability (semiconductor); Computer science; Statistics; Set (abstract data type); Stochastic process; Hazard; Econometrics; Process (computing); Algorithm; Data mining; Mathematics; Applied mathematics; Ecology; Engineering","score_opus":0.13021562141909196,"score_gpt":0.43285221441408644,"score_spread":0.30263659299499446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982580511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001320775,0.000015220866,0.9191225,0.00015496937,0.00018399314,0.00010196453,0.07889301,0.000067961475,0.00013956708],"genre_scores_gemma":[0.03919027,0.000007952769,0.88019663,0.00006943668,0.00012542651,0.000004257388,0.08036088,0.000020073761,0.000025075213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746585,0.00016093132,0.00063545123,0.00085658766,0.00063998956,0.00024122027],"domain_scores_gemma":[0.9906977,0.005999293,0.00034095024,0.002551563,0.00023780952,0.00017268983],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008377098,0.00021793136,0.0004613087,0.00018871378,0.0002002606,0.0002488467,0.0015686501,0.00008794394,0.0018884903],"category_scores_gemma":[0.0068234596,0.00020666055,0.00004330969,0.0007335247,0.00016697453,0.00038220553,0.00088187953,0.0003222696,0.00012634744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013230676,0.00014008042,0.001959079,0.000025554986,0.0011235427,0.000026395124,0.00005474094,0.0007363463,0.000023168997,0.723122,0.024243,0.24853286],"study_design_scores_gemma":[0.000098531644,0.000004959405,0.008296029,0.000004800051,0.0011611918,0.0000011343341,0.0000031638276,0.50306666,0.0000023770074,0.4867789,0.00045271736,0.00012954533],"about_ca_topic_score_codex":0.0007597645,"about_ca_topic_score_gemma":0.0011453875,"teacher_disagreement_score":0.5023303,"about_ca_system_score_codex":0.000017170012,"about_ca_system_score_gemma":0.00012816137,"threshold_uncertainty_score":0.9990239},"labels":[],"label_agreement":null},{"id":"W1982954151","doi":"10.1016/j.csda.2007.08.016","title":"Testing the random walk hypothesis through robust estimation of correlation","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Heteroscedasticity; Autocorrelation; Econometrics; Mathematics; Random walk; Statistics; Estimator; Random walk hypothesis; Pearson product-moment correlation coefficient; Outlier; Stock market","score_opus":0.14005398772141306,"score_gpt":0.28721921530771544,"score_spread":0.14716522758630238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982954151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018333185,0.0002510987,0.9775358,0.00006489825,0.000084214415,0.00012293314,0.003055149,0.000017179796,0.0005355415],"genre_scores_gemma":[0.5880707,0.000014673856,0.410154,0.00003403542,0.000031408057,0.000001585396,0.0016714958,0.000007446015,0.000014625804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829215,0.000028167784,0.0010033154,0.00036981067,0.00013140748,0.00017513934],"domain_scores_gemma":[0.9961708,0.0024520457,0.00067797943,0.0004821201,0.00018466526,0.000032395877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017629223,0.000120543176,0.00038240093,0.00021708308,0.00024621884,0.000059103804,0.000336827,0.000056179924,0.00008125644],"category_scores_gemma":[0.002556075,0.00011759115,0.00007908849,0.0011933178,0.00008782719,0.00030219142,0.00010016832,0.00011138763,0.000043424803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021017722,0.000029999394,0.030923456,0.000012434853,0.00021623907,7.601476e-7,0.00020031656,0.8765461,5.219512e-7,0.07975697,0.00029691105,0.0119952625],"study_design_scores_gemma":[0.00019730983,0.000008548529,0.19029096,0.0000047649664,0.00018652165,4.21739e-7,0.000013968533,0.68033206,8.513403e-7,0.12875152,0.000129159,0.000083922045],"about_ca_topic_score_codex":0.001962878,"about_ca_topic_score_gemma":0.00020888864,"teacher_disagreement_score":0.56973755,"about_ca_system_score_codex":0.000069247726,"about_ca_system_score_gemma":0.000043008426,"threshold_uncertainty_score":0.4795228},"labels":[],"label_agreement":null},{"id":"W1983033786","doi":"10.1016/j.csda.2013.11.020","title":"Confidence intervals for quantiles in finite populations with randomized nomination sampling","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Quantile; CDF-based nonparametric confidence interval; Statistics; Mathematics; Simple random sample; Robust confidence intervals; Sampling design; Nonparametric statistics; Population; Sampling (signal processing); Completely randomized design; Computer science; Medicine","score_opus":0.274551803250768,"score_gpt":0.45967893506991525,"score_spread":0.18512713181914725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983033786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010331708,0.000011524819,0.986857,0.00065052323,0.000022503777,0.0009873026,0.010335074,0.00004580003,0.000057083176],"genre_scores_gemma":[0.41727045,0.0000030962858,0.55985415,0.00007067179,0.000012052096,0.00028974863,0.02245474,0.000009931431,0.000035182908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805146,0.00013884911,0.000852529,0.00042807497,0.0003329824,0.00019610979],"domain_scores_gemma":[0.98877347,0.009614967,0.0003762181,0.0004290311,0.00071801356,0.0000882814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067396264,0.00017160742,0.0005559914,0.00032642428,0.00018032682,0.0001865921,0.0002947162,0.000046529127,0.0005230842],"category_scores_gemma":[0.0053112535,0.0001529261,0.00007900198,0.00085229037,0.00016530392,0.00029804336,0.00006951857,0.000088720204,0.00004485275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016463299,0.00010796768,0.00043099688,0.000036903075,0.00024229377,3.88699e-7,0.00006443876,0.050988242,0.0000013733925,0.94465804,0.0021345222,0.0011701862],"study_design_scores_gemma":[0.0031996237,0.0000067607643,0.011501541,0.000014912201,0.00047933185,4.2859307e-7,0.000020540765,0.527938,5.202325e-7,0.4567077,0.000029199018,0.000101466714],"about_ca_topic_score_codex":0.00043913772,"about_ca_topic_score_gemma":0.0005894082,"teacher_disagreement_score":0.48795038,"about_ca_system_score_codex":0.000063535335,"about_ca_system_score_gemma":0.0000744411,"threshold_uncertainty_score":0.635845},"labels":[],"label_agreement":null},{"id":"W1983095027","doi":"10.1016/j.csda.2011.05.015","title":"Trend filtering via empirical mode decompositions","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Agence Nationale de la Recherche","keywords":"Hilbert–Huang transform; Series (stratigraphy); Mode (computer interface); Empirical orthogonal functions; Nonparametric statistics; Time series; Empirical research; Key (lock); Decomposition; Econometrics; Mathematics; Computer science; Applied mathematics; Statistics; Geology; White noise","score_opus":0.10544316820241123,"score_gpt":0.35646488057632186,"score_spread":0.25102171237391063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983095027","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071861147,0.000036317037,0.99630076,0.0000819509,0.00005965179,0.000040260198,0.002113178,0.00008916876,0.0005601287],"genre_scores_gemma":[0.29224607,0.000005811921,0.7016115,0.000112145804,0.000033728196,0.0000034989873,0.005942135,0.000008048361,0.000037016704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979865,0.00008433294,0.0005191186,0.0006958214,0.00042373044,0.00029051732],"domain_scores_gemma":[0.9982159,0.00023419107,0.00020940698,0.0010533016,0.000114977905,0.00017219775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023002291,0.00018866781,0.00034563098,0.00040985792,0.00035492773,0.00023129916,0.001360735,0.00004159015,0.00042155918],"category_scores_gemma":[0.000039078765,0.00018820963,0.0001374449,0.0017243926,0.00007303216,0.00065650867,0.00088404637,0.00011814452,0.00005677288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032474916,0.00079251116,0.02135184,0.00003715627,0.0076380176,0.00023169938,0.0031018157,0.57841194,0.00004802957,0.18876693,0.019610578,0.179977],"study_design_scores_gemma":[0.000091928574,0.000024597663,0.030962106,0.0000031527943,0.0006751519,0.000009695186,0.000008309063,0.94280493,0.0000044664284,0.02455591,0.0006471634,0.00021259568],"about_ca_topic_score_codex":0.0005725326,"about_ca_topic_score_gemma":0.000651555,"teacher_disagreement_score":0.36439297,"about_ca_system_score_codex":0.000038993498,"about_ca_system_score_gemma":0.00004518256,"threshold_uncertainty_score":0.7674966},"labels":[],"label_agreement":null},{"id":"W1983211478","doi":"10.1016/j.csda.2013.02.026","title":"Power Lindley distribution and associated inference","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":391,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Kurtosis; Mathematics; Statistics; Estimator; Quantile; Skewness; Likelihood function; Applied mathematics; Order statistic; Shape parameter; Estimation theory; Confidence interval; M-estimator","score_opus":0.0739339679624813,"score_gpt":0.38468607930793175,"score_spread":0.31075211134545044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983211478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006220884,0.00001172688,0.9553889,0.00039441415,0.000019580595,0.00019444605,0.037521906,0.00007780381,0.00017035875],"genre_scores_gemma":[0.77385926,0.000008600886,0.15311433,0.00009854635,0.000010322352,0.000032951866,0.07277977,0.000008755009,0.00008748608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838775,0.000093064584,0.00049486314,0.0004135409,0.00040795252,0.00020282816],"domain_scores_gemma":[0.99625874,0.0022622927,0.00023304195,0.0004492617,0.00062264426,0.00017402454],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002639434,0.00015980503,0.00028494367,0.00009405417,0.00025584456,0.00021389338,0.00025856617,0.0000673769,0.0020081317],"category_scores_gemma":[0.003977709,0.00015872976,0.0000386909,0.000832973,0.00014988196,0.00024229012,0.00019129076,0.00012763008,0.00019473035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018453271,0.00016566411,0.0038708418,0.000011197191,0.00045490623,0.0000011143444,0.000029691788,0.00081606413,0.000002045025,0.94401306,0.048404388,0.0022291865],"study_design_scores_gemma":[0.0001222258,0.000008050135,0.23931886,0.0000039063952,0.0003563927,5.540624e-7,0.000009460365,0.43087992,4.027e-7,0.3288988,0.00029031085,0.000111117544],"about_ca_topic_score_codex":0.00015969189,"about_ca_topic_score_gemma":0.000049975355,"teacher_disagreement_score":0.8022745,"about_ca_system_score_codex":0.00006455266,"about_ca_system_score_gemma":0.000060625403,"threshold_uncertainty_score":0.99890417},"labels":[],"label_agreement":null},{"id":"W1984010604","doi":"10.1016/j.csda.2009.11.008","title":"Influence analyses of skew-normal/independent linear mixed models","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Skew; Mathematics; Generalized linear mixed model; Applied mathematics; Generalization; Mixed model; Multivariate statistics; Random effects model; Linear model; Extension (predicate logic); Multivariate normal distribution; Algorithm; Statistics; Computer science; Mathematical analysis","score_opus":0.20109673968014163,"score_gpt":0.4556272083600548,"score_spread":0.2545304686799132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984010604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008296225,0.000028752596,0.97084236,0.00018046453,0.000012060144,0.00014228023,0.020224905,0.000058945905,0.00021401623],"genre_scores_gemma":[0.53162044,0.000010308423,0.45618674,0.00008942207,0.000012977541,0.000004925828,0.01204169,0.0000060796638,0.000027420429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974843,0.00010278766,0.00093283976,0.00046343126,0.0007990722,0.00021756176],"domain_scores_gemma":[0.99647635,0.0012435421,0.00046053337,0.0008316985,0.00082361425,0.00016423104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003634955,0.00020033661,0.00048550687,0.00029712595,0.00017189082,0.0000536623,0.0005890228,0.00009067398,0.00030264334],"category_scores_gemma":[0.0010896756,0.00019981741,0.00010887825,0.0014198542,0.00012651923,0.00028233477,0.00012779827,0.00018237683,0.000038123144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008000845,0.00020674696,0.0001436645,0.000017605915,0.00041143622,0.0000026136759,0.000026693382,0.35420597,0.000024882997,0.6401173,0.0033795948,0.0014555062],"study_design_scores_gemma":[0.00014118913,0.0000147650435,0.034945246,0.0000056601625,0.001014074,0.0000010716043,0.0000062879058,0.5324528,0.000025637954,0.43124261,0.00003854137,0.00011209717],"about_ca_topic_score_codex":0.00013439578,"about_ca_topic_score_gemma":0.00004413484,"teacher_disagreement_score":0.5233242,"about_ca_system_score_codex":0.000048479687,"about_ca_system_score_gemma":0.00012015881,"threshold_uncertainty_score":0.81483173},"labels":[],"label_agreement":null},{"id":"W1984288371","doi":"10.1016/j.csda.2009.02.021","title":"A non-parametric iterative smoothing method for benchmarking and temporal distribution","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Benchmarking; Smoothing; Parametric statistics; Iterative method; Distribution (mathematics); Mathematics; Computer science; Mathematical optimization; Nonparametric statistics; Applied mathematics; Algorithm; Statistics; Mathematical analysis","score_opus":0.036868337678571964,"score_gpt":0.3661155301217258,"score_spread":0.32924719244315387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984288371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003098739,0.000096729826,0.99705315,0.00028065883,0.00006599393,0.00015451097,0.0019859863,0.000035490753,0.000017612098],"genre_scores_gemma":[0.13242708,0.000006374646,0.8572236,0.00030280644,0.00006062731,0.0000044648345,0.009952274,0.0000043274777,0.000018452358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981385,0.00017775624,0.0003964446,0.0006833058,0.0003692639,0.00023475153],"domain_scores_gemma":[0.9972454,0.0016046456,0.00022094396,0.00048259684,0.00034533942,0.000101086815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014537047,0.00017022775,0.00034767904,0.00036472245,0.00036707835,0.00066863676,0.0006023422,0.00004692665,0.0000054924885],"category_scores_gemma":[0.00043145128,0.0001691609,0.0000709437,0.0018507801,0.00003386684,0.00068030704,0.0002232227,0.00011475708,0.0000017642654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050565326,0.0001588068,0.0035114617,0.00003965564,0.0009647165,0.000043318218,0.0006155842,0.09970053,0.000044806835,0.15103544,0.009067718,0.7347674],"study_design_scores_gemma":[0.00032325115,0.000078629004,0.034347024,0.000007605607,0.00037272956,0.0000052455366,0.0000036472534,0.87526536,0.00000892982,0.088893004,0.00051941763,0.0001751816],"about_ca_topic_score_codex":0.00011836893,"about_ca_topic_score_gemma":0.000011191619,"teacher_disagreement_score":0.7755648,"about_ca_system_score_codex":0.000051373743,"about_ca_system_score_gemma":0.0000827682,"threshold_uncertainty_score":0.68981814},"labels":[],"label_agreement":null},{"id":"W1984352904","doi":"10.1016/j.csda.2003.11.018","title":"Improved interval estimation for the two-parameter Birnbaum–Saunders distribution","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mathematics; Statistics; Confidence interval; Interval estimation; Applied mathematics; Monte Carlo method; Interval (graph theory); Coverage probability; Sample size determination; Estimation theory; Maximum likelihood; Combinatorics","score_opus":0.10769325153403275,"score_gpt":0.412918148381323,"score_spread":0.30522489684729026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984352904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033146772,0.000017594168,0.94706166,0.0016355629,0.00007969952,0.000580511,0.050182328,0.00009663626,0.000014569456],"genre_scores_gemma":[0.4031921,0.000004073813,0.52986926,0.00015196379,0.000041246203,0.000118657015,0.06658114,0.000014656034,0.00002693464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799204,0.000064171385,0.0007144187,0.00052428665,0.0004288406,0.00027621535],"domain_scores_gemma":[0.9935336,0.004675707,0.00034803996,0.000790272,0.0005296775,0.00012266624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055786007,0.00022347072,0.00032517765,0.000105709965,0.00057398214,0.00023844632,0.00055844913,0.000057694888,0.00016397535],"category_scores_gemma":[0.0035045817,0.00018413512,0.00014715454,0.00092374976,0.00022675075,0.00022498009,0.00015285995,0.00014519028,0.000041335836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022604541,0.0001522335,0.00003397403,0.000028132046,0.00071527075,5.514373e-7,0.00003882818,0.14571227,0.0000037804737,0.8360922,0.008246165,0.008954005],"study_design_scores_gemma":[0.0005015767,0.000016871643,0.0025727693,0.000004984017,0.0013959024,0.0000016575576,0.000019845684,0.5722496,0.0000054952807,0.42273042,0.00037505562,0.00012585911],"about_ca_topic_score_codex":0.00020102847,"about_ca_topic_score_gemma":0.00023039572,"teacher_disagreement_score":0.4265373,"about_ca_system_score_codex":0.00021232072,"about_ca_system_score_gemma":0.00014479304,"threshold_uncertainty_score":0.75088125},"labels":[],"label_agreement":null},{"id":"W1984835905","doi":"10.1016/j.csda.2004.05.034","title":"Likelihood-ratio tests for normality","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normality; Statistics; Mathematics; Likelihood-ratio test; Omnibus test; Econometrics; Statistical hypothesis testing","score_opus":0.15519566241943772,"score_gpt":0.44137400416275296,"score_spread":0.28617834174331525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984835905","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040994756,0.00001052128,0.89511377,0.00063209434,0.00003479337,0.0003111348,0.103286855,0.00009277669,0.0001081008],"genre_scores_gemma":[0.23851456,0.0000033502367,0.68539226,0.00019049084,0.000050088893,0.000067180925,0.075734265,0.000013606243,0.00003419815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981027,0.000043175514,0.00064108946,0.00050216523,0.00044524934,0.0002655868],"domain_scores_gemma":[0.9963974,0.0018472828,0.00025328013,0.0007155115,0.00060474966,0.00018181387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004324671,0.0001820741,0.00033080057,0.000152906,0.00035906912,0.00013216246,0.00043083905,0.000057941365,0.00029485257],"category_scores_gemma":[0.0022211634,0.00018842633,0.00009628831,0.00092070893,0.000114954906,0.00019324878,0.00012542108,0.000093981915,0.000088007655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007754341,0.00023402846,0.00032661605,0.000037850215,0.0004241784,0.0000014049742,0.00002929241,0.018094169,0.0000032999599,0.9600145,0.019437801,0.0013890663],"study_design_scores_gemma":[0.00040276806,0.000015197382,0.02071425,0.000004341251,0.0009834617,0.0000013666248,0.000010441312,0.33952847,0.0000046135215,0.6372386,0.000939443,0.00015702062],"about_ca_topic_score_codex":0.000107281696,"about_ca_topic_score_gemma":0.0003635552,"teacher_disagreement_score":0.32277593,"about_ca_system_score_codex":0.00011554607,"about_ca_system_score_gemma":0.00021476256,"threshold_uncertainty_score":0.7683803},"labels":[],"label_agreement":null},{"id":"W1985075348","doi":"10.1016/j.csda.2014.06.001","title":"The bivariate Sinh-Elliptical distribution with applications to Birnbaum–Saunders distribution and associated regression and measurement error models","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Bivariate analysis; Mathematics; Generalization; Estimator; Statistics; Applied mathematics; Distribution (mathematics); Regression analysis; Marginal distribution; Random variable; Mathematical analysis","score_opus":0.13301483689107688,"score_gpt":0.36927558235586627,"score_spread":0.2362607454647894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985075348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006420018,0.000028608527,0.976556,0.0018707416,0.000014258377,0.0005038036,0.020275122,0.00007724779,0.00003222355],"genre_scores_gemma":[0.8271447,0.000029247218,0.13309696,0.000088890025,0.000028498462,0.00015336309,0.039413452,0.000018014709,0.000026858817],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997425,0.00021684865,0.000569844,0.00061954017,0.00087796693,0.0002907759],"domain_scores_gemma":[0.9959997,0.0019580415,0.00028385338,0.0006090283,0.00085394655,0.00029545987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011221754,0.000240084,0.00033343674,0.00007126256,0.00105884,0.00030245967,0.00027756847,0.00007416501,0.00001645168],"category_scores_gemma":[0.0018217129,0.00017691225,0.000035652796,0.001006194,0.0002933108,0.00016017548,0.00020296568,0.00015578077,0.000010918441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029653684,0.00013293873,0.0002736628,0.000022674563,0.00037686055,4.170263e-7,0.000023741442,0.01028054,0.0000026546506,0.9729845,0.007302394,0.008569983],"study_design_scores_gemma":[0.00027582987,0.000031540763,0.024602287,0.000018355046,0.0009490296,0.0000019583354,0.000024501454,0.6636861,0.000001026545,0.30773076,0.0025050663,0.0001735754],"about_ca_topic_score_codex":0.00007211108,"about_ca_topic_score_gemma":0.0002995343,"teacher_disagreement_score":0.843459,"about_ca_system_score_codex":0.00018327864,"about_ca_system_score_gemma":0.00008039891,"threshold_uncertainty_score":0.8143848},"labels":[],"label_agreement":null},{"id":"W1986114210","doi":"10.1016/j.csda.2008.08.001","title":"Finding approximate solutions to combinatorial problems with very large data sets using BIRCH","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"TRIUMF","keywords":"Outlier; Estimator; Computer science; Algorithm; Robustness (evolution); Covariance; Mathematical optimization; Mathematics; Statistics; Artificial intelligence","score_opus":0.38628780976680993,"score_gpt":0.463281868573303,"score_spread":0.07699405880649307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986114210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019135454,0.000031406365,0.94721514,0.000050185296,0.00010969865,0.0003318201,0.050242294,0.0000681506,0.00003778793],"genre_scores_gemma":[0.062485073,0.000013433017,0.916663,0.00006017542,0.000073534786,0.000012580771,0.020626785,0.000042413285,0.000023000022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996783,0.00021409358,0.000643008,0.0009653191,0.0008376685,0.00055691454],"domain_scores_gemma":[0.9953715,0.0021313855,0.00027942465,0.0015641543,0.00038953323,0.00026398158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010165314,0.00028347652,0.00062353845,0.00033671816,0.00082406163,0.00009632431,0.000933934,0.00006623077,0.000077887096],"category_scores_gemma":[0.0015427113,0.00026391,0.00004396367,0.0013816037,0.00013656066,0.000444732,0.0012774593,0.00022297575,0.000013792398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007551771,0.0006225843,0.001975744,0.00015752384,0.002011425,0.00011922218,0.00041929522,0.30973652,0.000011354949,0.67544883,0.0077445847,0.0016774222],"study_design_scores_gemma":[0.00042417712,0.00003388548,0.00054371177,0.000023024199,0.0010950826,0.000014786672,0.000017457798,0.68629205,5.9562825e-7,0.31083018,0.00047216535,0.00025291461],"about_ca_topic_score_codex":0.00014277254,"about_ca_topic_score_gemma":0.00017965239,"teacher_disagreement_score":0.3765555,"about_ca_system_score_codex":0.00011281862,"about_ca_system_score_gemma":0.0002524819,"threshold_uncertainty_score":0.9999813},"labels":[],"label_agreement":null},{"id":"W1986211349","doi":"10.1016/j.csda.2012.03.011","title":"Bootstrap variance estimation with survey data when estimating model parameters","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Sampling design; Statistics; Sampling (signal processing); Variance (accounting); Simple random sample; Stratified sampling; Mathematics; Inference; Population; Econometrics; Computer science; Artificial intelligence","score_opus":0.31892552233020255,"score_gpt":0.446430431089935,"score_spread":0.12750490875973247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986211349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022939066,0.000027102713,0.96098185,0.000045336707,0.00007125096,0.0001836945,0.03833071,0.00006395206,0.00006674187],"genre_scores_gemma":[0.041477114,0.0000025146053,0.9166991,0.000070114176,0.000048754777,0.000010453514,0.041637868,0.000032842596,0.000021239752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679196,0.0004315529,0.000734106,0.0007545647,0.0008217376,0.00046610937],"domain_scores_gemma":[0.9895571,0.007470761,0.00048025363,0.0018991379,0.00033621464,0.00025656636],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025424592,0.00030490616,0.000597949,0.00019636187,0.00025337934,0.00023837306,0.0011410128,0.000072561525,0.00016488353],"category_scores_gemma":[0.0061749024,0.00026905048,0.000033962846,0.00076902687,0.00017560748,0.00089312583,0.00054227957,0.00022288648,0.000025640362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006915961,0.00042196605,0.021115944,0.00017119097,0.0023116474,0.000011068056,0.00039664897,0.39190102,9.1640595e-7,0.502951,0.017225675,0.06342374],"study_design_scores_gemma":[0.00013456884,0.000013937277,0.013245199,0.000017023063,0.0012994078,0.0000034047862,0.000006175913,0.59039813,2.830424e-7,0.39466423,0.0000068901572,0.00021074191],"about_ca_topic_score_codex":0.00061134266,"about_ca_topic_score_gemma":0.00031380384,"teacher_disagreement_score":0.19849712,"about_ca_system_score_codex":0.00005669867,"about_ca_system_score_gemma":0.00018124074,"threshold_uncertainty_score":0.99997616},"labels":[],"label_agreement":null},{"id":"W1986961877","doi":"10.1016/j.csda.2007.09.024","title":"Improving the performance of kurtosis estimator","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kurtosis; Estimator; Mean squared error; Statistics; Mathematics; Population mean; Sample size determination; Econometrics; Computer science","score_opus":0.07903098624247747,"score_gpt":0.3852264816541854,"score_spread":0.30619549541170793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986961877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013612335,0.000014228055,0.97821283,0.00012588261,0.000027431666,0.00013840864,0.0077056987,0.000037594924,0.00012560251],"genre_scores_gemma":[0.56263494,0.0000030374101,0.4331851,0.00004060494,0.000018297296,0.0000053372373,0.004077565,0.000007016795,0.000028113795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982739,0.000042771924,0.000677673,0.00028969953,0.0005222351,0.00019368848],"domain_scores_gemma":[0.99525106,0.0031456256,0.00038316564,0.00069928734,0.00043147302,0.000089379355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009500177,0.00012817179,0.00025487097,0.00014451494,0.00029312994,0.000045955305,0.0005172123,0.000037006568,0.0003236105],"category_scores_gemma":[0.0014275463,0.000101823556,0.00005983919,0.0011405931,0.00020073431,0.00011409206,0.00017464676,0.000109512,0.000033663317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012519247,0.00012791538,0.0036844115,0.000064620166,0.00044016447,0.0000012699775,0.000042689928,0.008426697,0.000025556259,0.9686487,0.0060387473,0.012486708],"study_design_scores_gemma":[0.00012753211,0.0000129208465,0.09061138,0.0000055284995,0.0010452637,0.0000017834187,0.000024895513,0.8676605,0.000044274027,0.04014987,0.00020719154,0.00010882009],"about_ca_topic_score_codex":0.00009184121,"about_ca_topic_score_gemma":0.000055007815,"teacher_disagreement_score":0.9284988,"about_ca_system_score_codex":0.000040232106,"about_ca_system_score_gemma":0.000075577314,"threshold_uncertainty_score":0.4152244},"labels":[],"label_agreement":null},{"id":"W1988722509","doi":"10.1016/j.csda.2009.08.016","title":"Nonparametric density estimation for positive time series","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Center for Interuniversity Research and Analysis on Organizations; Université de Montréal","funders":"","keywords":"Mathematics; Estimator; Kernel density estimation; Stochastic volatility; Applied mathematics; Variable kernel density estimation; Independent and identically distributed random variables; Statistics; Kernel method; Random variable; Econometrics; Volatility (finance); Computer science; Artificial intelligence","score_opus":0.036462598678816995,"score_gpt":0.2806309131504767,"score_spread":0.24416831447165974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988722509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066274153,0.00016367539,0.9727678,0.00033296028,0.00004512595,0.00016061196,0.019732289,0.000027210575,0.00014292252],"genre_scores_gemma":[0.46271375,0.000017949082,0.5180043,0.0001218712,0.00003607235,0.0000030273052,0.01899168,0.000006344344,0.000105027364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986475,0.000014975414,0.00056889706,0.0005055891,0.00007766471,0.00018534997],"domain_scores_gemma":[0.99876475,0.00029307898,0.00030074763,0.0003812458,0.00019859396,0.0000615772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049125607,0.00013199453,0.0004216568,0.00044133147,0.00023455327,0.00012783955,0.00025279526,0.00005756251,0.00007747929],"category_scores_gemma":[0.0007507226,0.00016756976,0.000093219955,0.00096508884,0.00004556143,0.00041221606,0.000057292393,0.00007072193,0.0001537693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061456274,0.00013892174,0.008113209,0.000014080688,0.00048467866,0.0000025339018,0.00012370493,0.40180117,0.0000011353479,0.5675777,0.004406334,0.01727506],"study_design_scores_gemma":[0.00010571075,0.00003505459,0.10622289,0.0000016629673,0.0001373128,4.1255944e-7,0.0000012003303,0.57606775,9.758156e-7,0.31711492,0.00020491023,0.00010718167],"about_ca_topic_score_codex":0.00022288201,"about_ca_topic_score_gemma":0.000040744068,"teacher_disagreement_score":0.45608634,"about_ca_system_score_codex":0.000074383315,"about_ca_system_score_gemma":0.000035879544,"threshold_uncertainty_score":0.68332964},"labels":[],"label_agreement":null},{"id":"W1990572220","doi":"10.1016/j.csda.2013.02.019","title":"Generating beta random numbers and Dirichlet random vectors in R: The package rBeta2009","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random number generation; Software package; Computer science; Software; Dirichlet distribution; R package; Algorithm; Theoretical computer science; Parallel computing; Mathematics; Computational science; Programming language","score_opus":0.024027990918040656,"score_gpt":0.2945454916717646,"score_spread":0.27051750075372394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990572220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031086807,0.00035007522,0.99482054,0.0008445213,0.000060688366,0.00024429068,0.00042451418,0.000025330657,0.000121340854],"genre_scores_gemma":[0.19687472,0.00005411805,0.8009184,0.0007241363,0.00005345473,0.000019337931,0.0013238898,0.0000074277355,0.000024485353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749064,0.0006659501,0.0004772761,0.0006131546,0.00048466478,0.00026831473],"domain_scores_gemma":[0.99670374,0.0020260834,0.00017682926,0.0008607033,0.00013447294,0.00009814692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014292878,0.00019620004,0.00041588745,0.0002270197,0.00023968056,0.0006880358,0.0011422146,0.000047484828,0.000050078557],"category_scores_gemma":[0.00022112278,0.0001431686,0.000067403176,0.0011893254,0.00008686302,0.00055337104,0.0003668192,0.00018399299,0.000017345406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049511593,0.000349907,0.025594814,0.00007802867,0.0026598405,0.00013935483,0.0051052435,0.11190436,0.00009074149,0.3516548,0.09054372,0.41182968],"study_design_scores_gemma":[0.00095708657,0.000010651246,0.0233061,0.0000045052566,0.00027377575,0.000005678791,0.000014555741,0.9178985,0.0000013087995,0.057082128,0.00027048695,0.00017521724],"about_ca_topic_score_codex":0.00087777205,"about_ca_topic_score_gemma":0.00032063288,"teacher_disagreement_score":0.80599415,"about_ca_system_score_codex":0.000020430658,"about_ca_system_score_gemma":0.000057891582,"threshold_uncertainty_score":0.6634745},"labels":[],"label_agreement":null},{"id":"W1991251761","doi":"10.1016/s0167-9473(01)00042-1","title":"Series approximations for moments of order statistics using MAPLE","year":2002,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Maple; Mathematics; Series (stratigraphy); Approximations of π; Order statistic; Applied mathematics; Statistics","score_opus":0.2931880043136888,"score_gpt":0.4313168281483038,"score_spread":0.138128823834615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991251761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021089746,0.000016887076,0.8276842,0.00013512229,0.00003271507,0.0003240381,0.17146817,0.000038388138,0.00008956434],"genre_scores_gemma":[0.036466263,0.000010610724,0.92974794,0.000042460168,0.000028313494,0.000048805883,0.03329584,0.00002253693,0.0003372547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99788076,0.00006868213,0.0008782554,0.00041813453,0.0005170532,0.00023713648],"domain_scores_gemma":[0.9957836,0.0018132695,0.0004795191,0.00064910983,0.0011523713,0.00012207705],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026923517,0.00019604078,0.0004435362,0.00025202008,0.0003154102,0.00007769056,0.00038091722,0.00005809454,0.0016094332],"category_scores_gemma":[0.0021071653,0.00021055386,0.000068567446,0.0013090307,0.00019289984,0.00022079825,0.00013098677,0.000069346235,0.000022765253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007755622,0.00031010958,0.00023984344,0.00013821926,0.0006974055,8.118785e-7,0.00007558999,0.02436179,0.000008138467,0.9280884,0.044868633,0.0012032782],"study_design_scores_gemma":[0.00025081012,0.000015903144,0.00091489917,0.000005720907,0.0011176826,0.0000016537657,0.000025661962,0.64714915,0.000004087561,0.3494246,0.00095196714,0.00013789459],"about_ca_topic_score_codex":0.000042585372,"about_ca_topic_score_gemma":0.000053327134,"teacher_disagreement_score":0.62278736,"about_ca_system_score_codex":0.00006765009,"about_ca_system_score_gemma":0.00006654482,"threshold_uncertainty_score":0.9993032},"labels":[],"label_agreement":null},{"id":"W1991588369","doi":"10.1016/j.csda.2006.09.037","title":"A convenient way of generating gamma random variables using generalized exponential distribution","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Gamma distribution; Mathematics; Exponential function; Applied mathematics; Exponential distribution; Distribution (mathematics); Random variable; Generalized integer gamma distribution; Statistics; Mathematical optimization; Algorithm; Mathematical analysis","score_opus":0.08910429669507887,"score_gpt":0.36779745615470527,"score_spread":0.2786931594596264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991588369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020507755,0.000030935935,0.9259666,0.000044587516,0.000048239566,0.00021439159,0.053106368,0.0000463388,0.000034740428],"genre_scores_gemma":[0.41887137,0.0000028221173,0.49261487,0.000013602729,0.000062341875,0.0000135729615,0.08838588,0.000010513379,0.000025050755],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974209,0.00019024845,0.0010879228,0.00045410322,0.0006128503,0.0002339709],"domain_scores_gemma":[0.9969026,0.0012554867,0.00059613487,0.0005345495,0.000619301,0.00009192219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005124322,0.00020245751,0.0005110122,0.00014839986,0.00030245108,0.00009992264,0.00030191027,0.000066024775,0.0005976884],"category_scores_gemma":[0.0007996513,0.00020794506,0.0001163608,0.0009695349,0.00016079389,0.00013868627,0.00014805396,0.00008749478,0.000010423793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026353795,0.00023642708,0.0005223177,0.000041346684,0.00043914007,0.0000028088737,0.000014448716,0.20147942,0.00030542974,0.7879281,0.008566887,0.00043734786],"study_design_scores_gemma":[0.0008495098,0.0000068166128,0.005195521,0.000009563252,0.0017059762,0.0000029047742,0.000008054208,0.81879467,0.000068967114,0.17292912,0.00025632148,0.00017260214],"about_ca_topic_score_codex":0.00070848764,"about_ca_topic_score_gemma":0.00008240396,"teacher_disagreement_score":0.61731523,"about_ca_system_score_codex":0.00009933408,"about_ca_system_score_gemma":0.000111036665,"threshold_uncertainty_score":0.8479754},"labels":[],"label_agreement":null},{"id":"W1993531603","doi":"10.1016/j.csda.2012.09.003","title":"Exact statistical power for response adaptive designs","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Adaptive design; Markov chain; Statistical power; Mathematics; Sample size determination; Mathematical optimization; Power (physics); Applied mathematics; Computer science; Statistics","score_opus":0.7109912218851108,"score_gpt":0.5976965298666802,"score_spread":0.11329469201843057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993531603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045563225,0.00004634332,0.92460704,0.0001358325,0.00030766198,0.000555796,0.073697925,0.000081052574,0.00011274616],"genre_scores_gemma":[0.09093319,0.000005903905,0.9053898,0.00019556335,0.00023199196,0.00005121954,0.0030046236,0.00005966421,0.00012803714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9938907,0.0021022502,0.0014574182,0.00082512805,0.0009762792,0.0007482426],"domain_scores_gemma":[0.8061662,0.19139586,0.0004523746,0.0010213365,0.0005176684,0.00044657924],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00935098,0.00037663055,0.0011154587,0.00033801974,0.00025665667,0.00012004889,0.00075139507,0.00016865916,0.0018869685],"category_scores_gemma":[0.13661937,0.0003549907,0.00020249616,0.00090649864,0.0003389243,0.00028450455,0.0003877087,0.00027606366,0.00013585045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001913092,0.00069636776,0.0017285221,0.00006015863,0.0034648627,0.00001472642,0.00016022212,0.0011083196,0.000011984399,0.9088268,0.07669499,0.0053199218],"study_design_scores_gemma":[0.00078445463,0.00021041153,0.025526797,0.000011592978,0.004339288,0.0000034047891,0.000038817245,0.14930487,0.0000068061468,0.81716037,0.0021962365,0.00041694305],"about_ca_topic_score_codex":0.000028024862,"about_ca_topic_score_gemma":0.000013123601,"teacher_disagreement_score":0.18929362,"about_ca_system_score_codex":0.00014507168,"about_ca_system_score_gemma":0.00021909228,"threshold_uncertainty_score":0.9998902},"labels":[],"label_agreement":null},{"id":"W1993581462","doi":"10.1016/j.csda.2009.04.003","title":"Multivariate trees for mixed outcomes","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Categorical variable; Multivariate statistics; Multivariate analysis; Statistics; Tree (set theory); Outcome (game theory); Mathematics; Computer science; Mixed model; Econometrics; Combinatorics","score_opus":0.13898316285290196,"score_gpt":0.4511890468050191,"score_spread":0.3122058839521171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993581462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027053847,0.000012945313,0.97568387,0.00038198222,0.000076283264,0.00021935557,0.02322633,0.000060755014,0.00006796378],"genre_scores_gemma":[0.049010746,0.000002390984,0.94306433,0.00017213395,0.000049503855,0.000011086745,0.007602127,0.000013709038,0.00007398803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980431,0.00013414495,0.000598685,0.0005297988,0.000417433,0.00027681465],"domain_scores_gemma":[0.9912442,0.007374333,0.00024264373,0.0006836567,0.00032680726,0.00012834556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059833215,0.00021977385,0.0006125206,0.00021737674,0.00019295854,0.0001293901,0.00050851086,0.00005918096,0.00024388892],"category_scores_gemma":[0.0045764823,0.00018837597,0.00012758034,0.00053898914,0.00006484374,0.0001339864,0.000095813215,0.0000935949,0.000015004321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022698523,0.00018614809,0.002488559,0.000017499535,0.0009497569,0.0000045169168,0.000038011214,0.00069332944,0.0000029949765,0.914712,0.011302714,0.069581755],"study_design_scores_gemma":[0.00026596923,0.000026689278,0.1756577,0.0000034887553,0.0011445925,2.5234687e-7,0.000004398403,0.28736344,7.312475e-7,0.53517324,0.00022416304,0.00013533433],"about_ca_topic_score_codex":0.000057521447,"about_ca_topic_score_gemma":0.00010109532,"teacher_disagreement_score":0.37953877,"about_ca_system_score_codex":0.000031648353,"about_ca_system_score_gemma":0.000061169194,"threshold_uncertainty_score":0.7681749},"labels":[],"label_agreement":null},{"id":"W1993670676","doi":"10.1016/j.csda.2005.01.009","title":"-norm projection pursuit principal component analysis","year":2005,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Principal component analysis; Outlier; Projection pursuit; Mathematics; Norm (philosophy); Robust principal component analysis; Centroid; Sparse PCA; Projection (relational algebra); Pattern recognition (psychology); Artificial intelligence; Algorithm; Computer science; Statistics","score_opus":0.1930826002416092,"score_gpt":0.46887391550425145,"score_spread":0.2757913152626422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993670676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017715533,0.000044431294,0.9873941,0.00022059462,0.000056008335,0.00024454843,0.009865693,0.00010610667,0.0002969979],"genre_scores_gemma":[0.10884055,0.000022379209,0.8774862,0.00012157127,0.000141895,0.00002296457,0.013014077,0.000026199696,0.00032411233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964337,0.00025118326,0.0009488885,0.0009086949,0.0010512831,0.0004062919],"domain_scores_gemma":[0.99559104,0.0022446483,0.0004318314,0.0010495214,0.00045179203,0.00023117731],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010756262,0.00031088412,0.00082359643,0.0007568432,0.00030903294,0.00016079901,0.00065480784,0.00008455642,0.0006327236],"category_scores_gemma":[0.0010623026,0.00029904718,0.00023028036,0.0025067886,0.00012966762,0.00033301028,0.00040661127,0.00023538248,0.000050936265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048945916,0.0005143736,0.0024962828,0.00005235855,0.0104477415,0.000018733432,0.00018624212,0.40903,0.000008688057,0.5117905,0.0047810776,0.060625084],"study_design_scores_gemma":[0.00023752757,0.000024229475,0.0113597885,0.000003497916,0.010688386,0.0000022998897,0.0000145423755,0.75207925,0.000002719976,0.22206403,0.003251748,0.00027195367],"about_ca_topic_score_codex":0.00019439592,"about_ca_topic_score_gemma":0.0012049319,"teacher_disagreement_score":0.3430493,"about_ca_system_score_codex":0.00018422994,"about_ca_system_score_gemma":0.00009612967,"threshold_uncertainty_score":0.9999462},"labels":[],"label_agreement":null},{"id":"W1994836814","doi":"10.1016/s0167-9473(03)00093-8","title":"A variant of the Cox algorithm for the imputation of non-response of qualitative data","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Imputation (statistics); Weighting; Algorithm; Mathematics; Statistics; Computer science; Data mining; Missing data","score_opus":0.08250371196425887,"score_gpt":0.37307112958566624,"score_spread":0.29056741762140736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994836814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038053424,0.00006333877,0.9850816,0.00039771097,0.00005802486,0.00017911429,0.01381517,0.0000044138465,0.000020060254],"genre_scores_gemma":[0.3264647,0.000005479436,0.67145896,0.00003290215,0.000006934648,0.000005226445,0.0019818048,0.0000018862451,0.000042081443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979665,0.0004849033,0.0005890136,0.000385554,0.00044704962,0.00012695369],"domain_scores_gemma":[0.98988676,0.0069575976,0.00070881954,0.0016116315,0.00080600136,0.000029180297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031100996,0.00010892833,0.00029624946,0.00008443384,0.00013520307,0.00002786249,0.0021991273,0.000034592216,0.000020021052],"category_scores_gemma":[0.0029586928,0.000073472096,0.00007649237,0.0011662516,0.00021911475,0.00016708403,0.0006762797,0.00006604426,6.0040134e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012820943,0.00049643574,0.00076396257,0.000240038,0.0052766846,0.000005760156,0.008756518,0.7141083,0.00047665538,0.219355,0.01060793,0.039784532],"study_design_scores_gemma":[0.00024509654,0.000030159828,0.0056494097,0.00000940857,0.0005219293,0.000002475591,0.00023137715,0.9513616,0.00018559131,0.041150704,0.0005373336,0.00007488775],"about_ca_topic_score_codex":0.00019961558,"about_ca_topic_score_gemma":0.000025197236,"teacher_disagreement_score":0.3260842,"about_ca_system_score_codex":0.000011799212,"about_ca_system_score_gemma":0.00031229152,"threshold_uncertainty_score":0.40865624},"labels":[],"label_agreement":null},{"id":"W1995050491","doi":"10.1016/j.csda.2007.09.009","title":"Interacting sequential Monte Carlo samplers for trans-dimensional simulation","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Particle filter; Monte Carlo method; Importance sampling; Sampling (signal processing); Population; Resampling; Algorithm; Inference; Computer science; Convergence (economics); Slice sampling; Bayesian inference; Mathematical optimization; Statistical physics; State space; Hybrid Monte Carlo; Mathematics; Bayesian probability; Statistics; Artificial intelligence; Physics; Kalman filter; Filter (signal processing)","score_opus":0.09360254122331375,"score_gpt":0.4022379766698072,"score_spread":0.30863543544649347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995050491","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007532408,0.000043902673,0.996292,0.00015391715,0.00021971005,0.00017717185,0.0022773524,0.000057809568,0.000024881325],"genre_scores_gemma":[0.34032658,0.0000011638102,0.657285,0.00016690863,0.000082000646,0.0000027342962,0.0021024002,0.000008687476,0.00002456187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784255,0.000103821716,0.00056079775,0.0006868942,0.0004968834,0.00030906804],"domain_scores_gemma":[0.99572414,0.0029752257,0.00023648504,0.0005063374,0.00041626493,0.0001415662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014176384,0.00018042373,0.00030174857,0.0003540729,0.00026940586,0.00020603539,0.0007426753,0.000060103845,0.000029856501],"category_scores_gemma":[0.00030671468,0.00018647934,0.00013215576,0.000795058,0.00004259107,0.00057684747,0.00021517846,0.00012615559,0.0000036950541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028024198,0.00004223674,0.00016086563,0.000012382197,0.0005595876,0.000009866629,0.00024525527,0.8828508,0.000024783116,0.036003776,0.0008967599,0.079165645],"study_design_scores_gemma":[0.0002893369,0.00002293636,0.002940178,0.000006262761,0.000470566,0.0000026388525,0.000004757107,0.95731467,0.0000071313752,0.03737098,0.001370987,0.00019953324],"about_ca_topic_score_codex":0.00023342259,"about_ca_topic_score_gemma":0.00031231006,"teacher_disagreement_score":0.33957335,"about_ca_system_score_codex":0.00006828495,"about_ca_system_score_gemma":0.000093812996,"threshold_uncertainty_score":0.7604407},"labels":[],"label_agreement":null},{"id":"W1998705404","doi":"10.1016/j.csda.2011.02.011","title":"Inference on the probability as a measurement of treatment effect under a density ratio model and random censoring","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Censoring (clinical trials); Statistics; Inference; Econometrics; Mathematics; Random effects model; Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.7377686753371127,"score_gpt":0.5290462272621571,"score_spread":0.20872244807495555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998705404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046226785,0.000010573588,0.9513352,0.000054285698,0.000029227574,0.0005648054,0.0016476628,0.000018858374,0.000112636684],"genre_scores_gemma":[0.48678064,0.00001060727,0.5130738,0.000029631396,0.000010560003,0.000022907501,0.00005952893,0.000007069784,0.0000052595697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965587,0.0012452084,0.0008054365,0.0005210254,0.0007015198,0.00016810666],"domain_scores_gemma":[0.95110327,0.047099452,0.00038176787,0.0008600002,0.0004545802,0.000100948295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0042705564,0.000224761,0.0007864082,0.000088505454,0.00014531198,0.00003960408,0.00030151533,0.000057199384,0.00012775548],"category_scores_gemma":[0.04741522,0.00013961391,0.00010820266,0.0003206655,0.00025558082,0.000052726347,0.00019400829,0.00012327053,0.000006430977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006960349,0.0005596638,0.004596998,0.00011629064,0.0035981461,0.000004496507,0.00036345265,0.042792205,0.000023149614,0.9401231,0.00018788438,0.0069386093],"study_design_scores_gemma":[0.000605769,0.0001785914,0.007008844,0.000015954824,0.0020242834,3.306513e-7,0.0000053666363,0.39862445,0.00005734767,0.591396,8.325369e-7,0.00008224578],"about_ca_topic_score_codex":0.00029778157,"about_ca_topic_score_gemma":0.00019205143,"teacher_disagreement_score":0.44055387,"about_ca_system_score_codex":0.0001375382,"about_ca_system_score_gemma":0.00016859783,"threshold_uncertainty_score":0.9606088},"labels":[],"label_agreement":null},{"id":"W1998765560","doi":"10.1016/j.csda.2005.05.001","title":"Approximate inference for disease mapping","year":2005,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Inference; Markov chain Monte Carlo; Bayesian inference; Statistical inference; Computer science; Econometrics; Bayesian probability; Statistics; Mathematics; Data mining; Artificial intelligence","score_opus":0.4763931383410124,"score_gpt":0.482229353472815,"score_spread":0.005836215131802602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998765560","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012624463,0.00051339174,0.94145364,0.008229539,0.000093092225,0.00035529226,0.047916934,0.00004030204,0.0001353535],"genre_scores_gemma":[0.22751038,0.000054528628,0.7355633,0.004686881,0.00034881072,0.00009166007,0.031428948,0.000025166208,0.0002903599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99610037,0.00011013067,0.002579662,0.00075718306,0.00014208307,0.00031056305],"domain_scores_gemma":[0.9950705,0.0023776316,0.0013367085,0.00079259824,0.00017482541,0.00024769755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051712478,0.00017125685,0.00072016305,0.0005057768,0.00027704012,0.0001798235,0.00053542,0.000047614456,0.00053834583],"category_scores_gemma":[0.0039585126,0.0002308216,0.00011030469,0.0004942242,0.00006413288,0.0005671619,0.00015561585,0.00008173426,0.000676981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014729153,0.00013559539,0.05575088,0.00025374905,0.0010230764,9.413311e-7,0.00033979313,0.23970418,9.20037e-8,0.63002473,0.0702825,0.0024697266],"study_design_scores_gemma":[0.00026872198,0.0000065081645,0.049515337,0.000009139764,0.00013097387,1.8608787e-7,0.000028636492,0.79811245,3.107114e-8,0.10841816,0.04330122,0.00020864676],"about_ca_topic_score_codex":0.00025066693,"about_ca_topic_score_gemma":0.00018797255,"teacher_disagreement_score":0.55840826,"about_ca_system_score_codex":0.00023400078,"about_ca_system_score_gemma":0.0001817821,"threshold_uncertainty_score":0.9412632},"labels":[],"label_agreement":null},{"id":"W1999882329","doi":"10.1016/j.csda.2010.11.017","title":"Ensemble classification of paired data","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Deutsche Forschungsgemeinschaft","keywords":"Resampling; Linear discriminant analysis; Random forest; Boosting (machine learning); Artificial intelligence; Logistic regression; Statistics; Computer science; Pattern recognition (psychology); Bootstrap aggregating; Gradient boosting; Machine learning; Mathematics","score_opus":0.34847954602819103,"score_gpt":0.4900812899065639,"score_spread":0.14160174387837288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999882329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001465772,0.0000126065115,0.9677617,0.00009686649,0.000090880334,0.00012888706,0.030197397,0.000035317724,0.00021056888],"genre_scores_gemma":[0.19314,0.000007634348,0.7814763,0.000023695919,0.000046896967,0.000004152608,0.02522677,0.000016170914,0.000058345406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777454,0.00013765586,0.000698162,0.0006560362,0.0005414633,0.00019215838],"domain_scores_gemma":[0.9928268,0.003907555,0.00041960148,0.0023007547,0.00042566436,0.00011957857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010619028,0.00016074529,0.00045626145,0.0001843985,0.00011687085,0.00004236113,0.0010839185,0.00007096833,0.0002508655],"category_scores_gemma":[0.0045906818,0.00015450768,0.000045935365,0.0006456198,0.00017130483,0.00026649976,0.0005556222,0.00020818543,0.000012144498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017836097,0.0002135303,0.00095316966,0.000063684674,0.00071806443,0.0000049150312,0.00004601369,0.0020321088,0.00048569022,0.9313731,0.0105844205,0.053507473],"study_design_scores_gemma":[0.000106064035,0.000008696429,0.0065969583,0.0000027582419,0.00087543944,9.788599e-7,0.000008293214,0.5269997,0.000006538972,0.46458372,0.00071478414,0.00009603835],"about_ca_topic_score_codex":0.000088120694,"about_ca_topic_score_gemma":0.0005610223,"teacher_disagreement_score":0.5249676,"about_ca_system_score_codex":0.0000132493215,"about_ca_system_score_gemma":0.00011399794,"threshold_uncertainty_score":0.630064},"labels":[],"label_agreement":null},{"id":"W2000206349","doi":"10.1016/j.csda.2004.07.027","title":"Comparisons of improved risk estimators of the multivariate mean vector","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Saint Mary's University","funders":"","keywords":"Multivariate statistics; Mathematics; Estimator; Statistics; Multivariate analysis; Multivariate normal distribution","score_opus":0.12025243768705568,"score_gpt":0.4349043985277346,"score_spread":0.3146519608406789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000206349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004140355,0.000022293938,0.9700162,0.000041821906,0.00006138667,0.00017938654,0.02549964,0.000016731658,0.000022173443],"genre_scores_gemma":[0.37398458,0.0000042529805,0.62539756,0.000008614266,0.000009646533,0.0000029128691,0.0005730593,0.0000116717465,0.000007686865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795574,0.00021368892,0.00081253017,0.00036890403,0.00046623367,0.00018290515],"domain_scores_gemma":[0.9947523,0.003028307,0.00085329387,0.00089001306,0.00038966036,0.000086436536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000556703,0.00017697133,0.0006170054,0.0001206017,0.00014374183,0.000016461438,0.0005883086,0.00004791757,0.000045125034],"category_scores_gemma":[0.0031944334,0.00013300155,0.00013393277,0.0007531799,0.00026102745,0.00008614565,0.00032866496,0.00017115514,0.0000017742714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028701064,0.0002980065,0.0019287126,0.00008372554,0.0015119741,0.0000014658382,0.00025865558,0.35313526,0.0000853003,0.6398562,0.0003316053,0.0024803672],"study_design_scores_gemma":[0.0003298776,0.000019267534,0.016165966,0.000014276889,0.0017401087,4.1576814e-7,0.000016935677,0.51178217,0.00005207566,0.46977228,0.000016890184,0.000089727946],"about_ca_topic_score_codex":0.0011360393,"about_ca_topic_score_gemma":0.00051216135,"teacher_disagreement_score":0.36984423,"about_ca_system_score_codex":0.000045217486,"about_ca_system_score_gemma":0.00014179244,"threshold_uncertainty_score":0.5423646},"labels":[],"label_agreement":null},{"id":"W2001572404","doi":"10.1016/j.csda.2007.09.021","title":"On the hazard function of Birnbaum–Saunders distribution and associated inference","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":141,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Estimator; Hazard; Monte Carlo method; Statistics; Mathematics; Function (biology); Inference; Applied mathematics; Statistical inference; Survival function; Cumulative distribution function; Econometrics; Computer science; Probability density function; Artificial intelligence","score_opus":0.10754271355551252,"score_gpt":0.3887252636804368,"score_spread":0.28118255012492427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001572404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012694742,0.000006984816,0.9651434,0.0003307312,0.00002382329,0.00014634588,0.021497732,0.00003543769,0.000120802855],"genre_scores_gemma":[0.9424853,0.0000060721436,0.02864971,0.00011376488,0.00001054937,0.0000067472647,0.028695138,0.0000069400717,0.000025777123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842876,0.0000947707,0.000531011,0.00029335558,0.00049272476,0.00015939631],"domain_scores_gemma":[0.99115473,0.007575182,0.00034409072,0.00041052682,0.00043242399,0.00008305806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095232605,0.00012920989,0.00023259956,0.00010610455,0.00025875677,0.000055302575,0.00021392383,0.000054549364,0.00026116456],"category_scores_gemma":[0.005280836,0.00010514521,0.000044070355,0.0010174658,0.0002174035,0.000079072604,0.00009346133,0.0001272484,0.000016800754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018470279,0.00013422748,0.0012929237,0.000012099872,0.00041752026,5.850143e-7,0.00001980676,0.001859844,0.0000035569985,0.9827814,0.011034712,0.0024248576],"study_design_scores_gemma":[0.00013241249,0.000022668597,0.21431494,0.000007218493,0.0006682923,2.3103676e-7,0.000025808742,0.28693727,0.0000034231614,0.4977039,0.0001048603,0.00007897986],"about_ca_topic_score_codex":0.00004603688,"about_ca_topic_score_gemma":0.00017687281,"teacher_disagreement_score":0.9364937,"about_ca_system_score_codex":0.000067256464,"about_ca_system_score_gemma":0.000051528426,"threshold_uncertainty_score":0.6322036},"labels":[],"label_agreement":null},{"id":"W2001651879","doi":"10.1016/j.csda.2011.12.021","title":"Cramér–von Mises and characteristic function tests for the two and -sample problems with dependent data","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Mathematics; von Mises yield criterion; Statistics; von Mises distribution; Sample (material); Applied mathematics; Physics; Finite element method","score_opus":0.19377709523187392,"score_gpt":0.4103966789893104,"score_spread":0.2166195837574365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001651879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010098924,0.00012059102,0.93138665,0.00031588486,0.00002637692,0.00040642402,0.06669228,0.0000332506,0.000008624638],"genre_scores_gemma":[0.5120181,0.000031287673,0.44038656,0.000096182666,0.00006670842,0.00007366035,0.047289927,0.000014097465,0.000023499693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986476,0.00005305694,0.00035502343,0.00041263647,0.00032091537,0.00021076808],"domain_scores_gemma":[0.9911726,0.0074791103,0.00022363682,0.0007395818,0.0002442045,0.00014086073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052736985,0.00016029886,0.00023545053,0.000074815325,0.00044635043,0.00018732269,0.00030143588,0.000028409677,0.00010788377],"category_scores_gemma":[0.0020407864,0.00011685679,0.000015489497,0.0003329979,0.00016771705,0.00029981136,0.0002582021,0.00008233677,0.0000063093594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061321814,0.0003440525,0.018537968,0.00020081234,0.0015883916,6.6710805e-7,0.00013198386,0.0027781806,0.00000851378,0.93835735,0.012005382,0.02598539],"study_design_scores_gemma":[0.00037936054,0.000024604267,0.16647671,0.000008579197,0.003166796,0.0000061227397,0.000033337918,0.7203729,3.6030963e-7,0.107243836,0.0021353408,0.00015206543],"about_ca_topic_score_codex":0.00014553753,"about_ca_topic_score_gemma":0.00030372178,"teacher_disagreement_score":0.8311135,"about_ca_system_score_codex":0.000022580774,"about_ca_system_score_gemma":0.000043667675,"threshold_uncertainty_score":0.47652814},"labels":[],"label_agreement":null},{"id":"W2001655697","doi":"10.1016/j.csda.2011.06.034","title":"Inference about clustering and parametric assumptions in covariance matrix estimation","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Robustness (evolution); Estimator; Mathematics; Cluster analysis; Covariance matrix; Statistical hypothesis testing; Inference; Estimation of covariance matrices; Heteroscedasticity; Robust statistics; Computer science; Mathematical optimization; Statistics; Artificial intelligence","score_opus":0.300071717291673,"score_gpt":0.49233053910598507,"score_spread":0.1922588218143121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001655697","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014660569,0.00007062877,0.99512917,0.000017200382,0.00003285441,0.00014475234,0.0030230454,0.00003275755,0.00008354825],"genre_scores_gemma":[0.22945021,0.000055383087,0.7692831,0.00002107253,0.00000891217,0.000012505456,0.0011315321,0.000011138963,0.000026107415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828774,0.0001489943,0.0005769192,0.0004789103,0.00029323922,0.00021419386],"domain_scores_gemma":[0.9958597,0.0032042796,0.0002263399,0.0004504811,0.00015427986,0.0001049426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006065132,0.00016462004,0.00038833433,0.00044066712,0.000117713134,0.00006685115,0.00025378805,0.00005608117,0.00013895478],"category_scores_gemma":[0.0031456572,0.00017014067,0.000027839238,0.0010908378,0.00010054766,0.00030049827,0.00024031819,0.00015613738,0.000010305281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021831791,0.00014399225,0.005227366,0.00009715971,0.00028066445,0.00002203943,0.00027126283,0.22074331,0.0000011786219,0.7336314,0.00014191597,0.03941788],"study_design_scores_gemma":[0.00012329251,0.000009923482,0.04070899,0.000012199683,0.00029514177,0.0000014045465,0.0000070540805,0.524348,2.34109e-7,0.4343843,0.000010354001,0.000099092205],"about_ca_topic_score_codex":0.00030796786,"about_ca_topic_score_gemma":0.0004825383,"teacher_disagreement_score":0.3036047,"about_ca_system_score_codex":0.000047486592,"about_ca_system_score_gemma":0.000049250877,"threshold_uncertainty_score":0.69381356},"labels":[],"label_agreement":null},{"id":"W2004939947","doi":"10.1016/j.csda.2007.04.018","title":"Mixture cure models for multivariate survival data","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Censoring (clinical trials); Statistics; Covariate; Multivariate statistics; Bivariate analysis; Jackknife resampling; Mathematics; Survival analysis; Marginal model; Survival function; Marginal distribution; Random effects model; Multivariate analysis; Econometrics; Correlation; Regression analysis; Medicine; Random variable; Internal medicine","score_opus":0.10922552757236624,"score_gpt":0.3880269756108853,"score_spread":0.27880144803851903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004939947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007677857,0.00017056067,0.9775237,0.00042117308,0.00029679228,0.00022471341,0.021117743,0.00008623282,0.00015142634],"genre_scores_gemma":[0.011569146,0.000022142238,0.9503093,0.00030553722,0.00018297756,0.0000045227944,0.037477225,0.000019514662,0.000109658904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673176,0.00016091952,0.0006215435,0.0013559243,0.00067393394,0.00045589337],"domain_scores_gemma":[0.99407005,0.0019222992,0.00028217694,0.003008758,0.00049377553,0.00022294796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029783328,0.00026720008,0.0004850928,0.00033288077,0.00029506095,0.00032820975,0.0040854244,0.00010970263,0.000019241237],"category_scores_gemma":[0.00031327392,0.0002550517,0.00009374362,0.001319437,0.000065150736,0.0011540384,0.0018086156,0.00019031687,0.000009110466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022080636,0.00011068461,0.0001177793,0.00002524557,0.001126122,0.000021849559,0.00013859748,0.065331675,0.0000066490475,0.8140328,0.020848067,0.098218426],"study_design_scores_gemma":[0.00025578044,0.000012013437,0.0012058943,0.0000035902217,0.000494224,0.0000020210052,0.00000265947,0.6687246,0.0000014341306,0.32581705,0.003271025,0.00020967904],"about_ca_topic_score_codex":0.00024072436,"about_ca_topic_score_gemma":0.0004154935,"teacher_disagreement_score":0.60339296,"about_ca_system_score_codex":0.000039163206,"about_ca_system_score_gemma":0.000182942,"threshold_uncertainty_score":0.99999017},"labels":[],"label_agreement":null},{"id":"W2006312194","doi":"10.1016/j.csda.2008.02.029","title":"On the power transformation of kernel-based tests for serial correlation in vector time series: Some finite sample results and a comparison with the bootstrap","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Statistics; Estimator; Series (stratigraphy); Statistical hypothesis testing; Autocorrelation; Kernel density estimation; Multivariate statistics; Applied mathematics","score_opus":0.07026727298365916,"score_gpt":0.27769764692968785,"score_spread":0.2074303739460287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006312194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13201256,0.000052096548,0.8457315,0.0005219818,0.00002157122,0.00023676433,0.021400664,0.000005569412,0.000017311588],"genre_scores_gemma":[0.9716065,0.0000147065075,0.021148542,0.00006486782,0.000015732396,0.000012727764,0.0071205627,0.000007487312,0.000008882864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989192,0.0000318867,0.0005911214,0.00025682477,0.00008861976,0.000112372145],"domain_scores_gemma":[0.9965579,0.002710929,0.00035238877,0.0002675886,0.000088607834,0.00002256601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057638175,0.000103143146,0.00029718925,0.00016569477,0.00019565226,0.000036720565,0.0001619807,0.00003996128,0.00002220703],"category_scores_gemma":[0.0007219381,0.000079512145,0.000038897753,0.00040978816,0.000105716164,0.00021148649,0.000017536597,0.00008846905,0.0000051079023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046224074,0.00006993024,0.011603121,0.0000132655205,0.00010888868,3.099961e-7,0.0010404175,0.89348817,4.830115e-7,0.092514925,0.0005676679,0.00013060201],"study_design_scores_gemma":[0.00060388516,0.0001149724,0.12993075,0.000007631137,0.00005476049,1.3983149e-7,0.000020782898,0.8449004,0.0000010690195,0.024013318,0.0002703252,0.00008193988],"about_ca_topic_score_codex":0.00045456056,"about_ca_topic_score_gemma":0.00048401576,"teacher_disagreement_score":0.83959395,"about_ca_system_score_codex":0.000029965177,"about_ca_system_score_gemma":0.000053468113,"threshold_uncertainty_score":0.32424113},"labels":[],"label_agreement":null},{"id":"W2006462491","doi":"10.1016/j.csda.2009.04.021","title":"Maximum likelihood estimation in vector long memory processes via EM algorithm","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Expectation–maximization algorithm; Univariate; Autoregressive model; Mathematics; Maximum likelihood sequence estimation; Algorithm; Multivariate statistics; Restricted maximum likelihood; Maximum likelihood; Computation; Likelihood function; Estimation theory; Gaussian process; Multivariate normal distribution; Statistics; Gaussian","score_opus":0.03117881384151132,"score_gpt":0.2725752397900063,"score_spread":0.24139642594849497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006462491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008397687,0.0008163621,0.98522985,0.0001406239,0.000070272385,0.00012652714,0.0051117726,0.00003124305,0.00007567698],"genre_scores_gemma":[0.59237957,0.00007003338,0.3979894,0.000105211344,0.000044211552,0.0000046126834,0.009382342,0.000009863408,0.000014801194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981098,0.00002155975,0.0008461618,0.000628907,0.00012716184,0.00026638352],"domain_scores_gemma":[0.9988193,0.00017716565,0.00033132156,0.00043820657,0.00015523931,0.000078765086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055625354,0.00017279088,0.00047215112,0.0005624692,0.00012996046,0.00014401792,0.00037123356,0.000072767005,0.0001255542],"category_scores_gemma":[0.00044220808,0.00021990498,0.000057356654,0.0014970216,0.00002785629,0.00047420428,0.0000804887,0.00014708073,0.00011887222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022116621,0.00040166886,0.036222935,0.00007535063,0.00034021543,0.000027328837,0.0006192864,0.5354468,3.6188453e-7,0.012110755,0.00075403135,0.4139791],"study_design_scores_gemma":[0.00015402454,0.000018051884,0.17408583,0.0000061120154,0.000066364846,6.1358975e-7,0.000006303269,0.59526896,4.73094e-7,0.23020668,0.000045369776,0.00014120401],"about_ca_topic_score_codex":0.00072278985,"about_ca_topic_score_gemma":0.000978655,"teacher_disagreement_score":0.58724046,"about_ca_system_score_codex":0.000107547145,"about_ca_system_score_gemma":0.000089211935,"threshold_uncertainty_score":0.89674646},"labels":[],"label_agreement":null},{"id":"W2007180500","doi":"10.1016/j.csda.2009.01.003","title":"Parametric sensitivity: A case study comparison","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"American University of Sharjah; University of Sharjah","keywords":"Sensitivity (control systems); Parametric statistics; Mathematics; Applied mathematics; Parametric model; Nonlinear system; Regression analysis; Statistics; Engineering","score_opus":0.25161246762953865,"score_gpt":0.4585212768646224,"score_spread":0.20690880923508376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007180500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033518665,0.000059270307,0.96461314,0.00009853294,0.000084166124,0.00019301947,0.0013299341,0.000057024277,0.000046249086],"genre_scores_gemma":[0.78388,0.0000011728346,0.21499628,0.00007467236,0.000040699117,0.0000017868757,0.00093877834,0.0000057048396,0.00006090641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567217,0.0004990026,0.0009727222,0.00090170704,0.0016998344,0.00025457705],"domain_scores_gemma":[0.991039,0.006462468,0.00030456355,0.0013804777,0.0006260708,0.0001874121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037050566,0.00020708397,0.0006638499,0.0010657203,0.00029158767,0.00047463924,0.0006491475,0.000047338388,0.00012803069],"category_scores_gemma":[0.0058709094,0.0001722001,0.000090511254,0.005452312,0.00006886853,0.0002553941,0.00023412837,0.0001789793,0.00013743648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008661951,0.0004959159,0.021075748,0.0000012716525,0.00044700547,0.0021988715,0.00019777728,0.9308193,3.045233e-7,0.0032395679,0.01189715,0.029618459],"study_design_scores_gemma":[0.00021249925,0.00009678946,0.08810344,0.000001232543,0.0010225258,0.0001455508,0.00033690964,0.88813984,9.3240025e-8,0.021537887,0.0002165651,0.0001866883],"about_ca_topic_score_codex":0.00048194,"about_ca_topic_score_gemma":0.0003772378,"teacher_disagreement_score":0.7503613,"about_ca_system_score_codex":0.000053731765,"about_ca_system_score_gemma":0.000104249164,"threshold_uncertainty_score":0.7028451},"labels":[],"label_agreement":null},{"id":"W2013989095","doi":"10.1016/j.csda.2008.11.033","title":"Escaping RGBland: Selecting colors for statistical graphics","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":209,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Categorical variable; Hue; Graphics; Artificial intelligence; Computer science; Luminance; Color space; HSL and HSV; Statistical graphics; Coding (social sciences); Computer vision; Computer graphics (images); RGB color model; Mathematics; Statistics","score_opus":0.04945520726689731,"score_gpt":0.3684192233551133,"score_spread":0.318964016088216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013989095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009536513,0.000041989944,0.9923673,0.00039243896,0.00007445441,0.00014482303,0.0067033935,0.00012332456,0.00005689489],"genre_scores_gemma":[0.12933758,0.000023371234,0.83752185,0.0012725219,0.00007285864,0.000004400411,0.031714562,0.000010097771,0.00004274572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758726,0.00010531692,0.00058979605,0.0007732234,0.00059097866,0.0003533935],"domain_scores_gemma":[0.99703205,0.0012499377,0.0002573496,0.00078491645,0.0004943484,0.00018139105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071625435,0.00020569768,0.00037914858,0.0004852795,0.00040734868,0.0005976312,0.0013139346,0.00005673454,0.000040741023],"category_scores_gemma":[0.00079064665,0.00021639102,0.00007990404,0.0021959273,0.000058814396,0.000569139,0.00024486583,0.0001238975,0.000017958911],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007965893,0.00012395711,0.00096399325,0.000017223516,0.0005250759,0.000010267238,0.00009830343,0.045277067,0.000003092022,0.8954924,0.039805606,0.01767507],"study_design_scores_gemma":[0.00027541726,0.00006480863,0.0103683,0.0000053000244,0.00050207693,0.0000028280676,0.000009502364,0.8848414,0.0000017499657,0.10028722,0.003403117,0.00023832018],"about_ca_topic_score_codex":0.00004693658,"about_ca_topic_score_gemma":0.00008522395,"teacher_disagreement_score":0.83956426,"about_ca_system_score_codex":0.000046483146,"about_ca_system_score_gemma":0.00016864734,"threshold_uncertainty_score":0.88241696},"labels":[],"label_agreement":null},{"id":"W2014057084","doi":"10.1016/j.csda.2010.08.010","title":"Analyzing dependent proportions in cluster randomized trials: Modeling inter-cluster correlation via copula function","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Copula (linguistics); Mathematics; Correlation; Cluster (spacecraft); Statistics; Econometrics; Computer science","score_opus":0.12220970426581963,"score_gpt":0.4206989497888344,"score_spread":0.29848924552301476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014057084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009829247,0.000015307238,0.9931935,0.00013291746,0.00032892925,0.00066475355,0.0045608105,0.000050697214,0.000070176015],"genre_scores_gemma":[0.2437489,0.0000062612253,0.7447757,0.00005168386,0.00009776675,0.00006352718,0.0112006515,0.000021710275,0.000033762237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945859,0.0016111668,0.0022062126,0.0007105641,0.0005908248,0.00029534058],"domain_scores_gemma":[0.9811224,0.01671434,0.0008174528,0.0006973296,0.00051030633,0.00013820268],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00794336,0.00028900694,0.001454467,0.0007293388,0.00020064786,0.00022441921,0.0003726157,0.00015369116,0.0020777476],"category_scores_gemma":[0.025265638,0.0002482919,0.00023375949,0.0009693874,0.00013276808,0.00034036092,0.00024483606,0.00054652937,0.00003524712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0072039324,0.0007267106,0.004648536,0.0001887101,0.004516825,0.00003262538,0.0003998819,0.29976863,0.000027374059,0.5584228,0.0066416548,0.11742234],"study_design_scores_gemma":[0.0050061555,0.00000984301,0.00032155061,0.000017393791,0.0023602918,0.0000025612244,0.000012908191,0.5516055,2.585099e-7,0.44049463,0.000014068067,0.00015480608],"about_ca_topic_score_codex":0.0005032923,"about_ca_topic_score_gemma":0.002610378,"teacher_disagreement_score":0.25183693,"about_ca_system_score_codex":0.00007589149,"about_ca_system_score_gemma":0.000120417026,"threshold_uncertainty_score":0.99999696},"labels":[],"label_agreement":null},{"id":"W2015450719","doi":"10.1016/j.csda.2011.06.029","title":"One-step minimum Hellinger distance estimation","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hellinger distance; Mathematics; Estimation; Statistics; Algorithm; Economics","score_opus":0.07208989895211289,"score_gpt":0.2895350957953323,"score_spread":0.21744519684321945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015450719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019180958,0.0001211399,0.996199,0.000076689335,0.00023156565,0.00007980753,0.002596753,0.00015092462,0.00035232442],"genre_scores_gemma":[0.1719554,0.000037301732,0.8176697,0.00016114506,0.000052959418,0.000004351577,0.010041985,0.000010592214,0.000066567365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759704,0.00010839866,0.00053989975,0.0008206927,0.00064573024,0.00028825807],"domain_scores_gemma":[0.9972638,0.0004836215,0.00027532002,0.0015430074,0.00028202016,0.00015224282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004020406,0.00018627582,0.0003082132,0.0002653659,0.00026609408,0.0002549866,0.0017016879,0.000062495244,0.00022239928],"category_scores_gemma":[0.00014198202,0.00020469257,0.00006831649,0.0013714987,0.00008992255,0.00069486746,0.0005617969,0.0001530287,0.00019348164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027479042,0.0004207199,0.0046157176,0.000036233752,0.0012099666,0.000052259147,0.00062137743,0.38443148,0.000002392552,0.4255406,0.036334723,0.14670707],"study_design_scores_gemma":[0.00013274259,0.000017917759,0.018823175,0.000010192073,0.0003619743,0.0000018976758,0.0000045099555,0.9304856,0.0000028329189,0.047788966,0.0021364116,0.00023380475],"about_ca_topic_score_codex":0.00022050212,"about_ca_topic_score_gemma":0.00011712225,"teacher_disagreement_score":0.5460541,"about_ca_system_score_codex":0.000032784264,"about_ca_system_score_gemma":0.00006547482,"threshold_uncertainty_score":0.834712},"labels":[],"label_agreement":null},{"id":"W2015733689","doi":"10.1016/j.csda.2008.11.015","title":"Strong convergence rate of estimators of change point and its application","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Probability and Risk Models","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; CUSUM; Mathematics; Rate of convergence; Sequence (biology); Convergence (economics); Moment (physics); Applied mathematics; Point (geometry); Change detection; Statistics; Algorithm; Combinatorics; Computer science; Artificial intelligence; Geometry","score_opus":0.3635850956380579,"score_gpt":0.43068548408972435,"score_spread":0.06710038845166644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015733689","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113953575,0.00018047931,0.8802317,0.00009121995,0.000020548543,0.00011847333,0.005386768,0.0000054076345,0.000011866478],"genre_scores_gemma":[0.9183864,0.00009564429,0.08022417,0.000020960053,0.000010006122,0.000005177058,0.0012419134,0.0000030920671,0.00001264722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979564,0.00014465659,0.0007129635,0.00043482854,0.00065360195,0.00009755876],"domain_scores_gemma":[0.9967742,0.0013679839,0.00050089194,0.0005530051,0.0007295105,0.00007441546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013295069,0.000089062814,0.0003620708,0.00027407828,0.00010745328,0.00001630409,0.00053507363,0.00003197197,0.00010829274],"category_scores_gemma":[0.0010532018,0.00007498304,0.00004566975,0.0011287282,0.00022632134,0.00035184185,0.0002756175,0.00004948083,0.000014282585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007067179,0.00030239386,0.22302462,0.000079087295,0.0008272267,0.000007512566,0.0015479409,0.47981036,0.00009560508,0.27085748,0.0019533213,0.021423774],"study_design_scores_gemma":[0.000082761086,0.000013695466,0.16841255,0.0000024053809,0.00014034125,0.0000011693709,0.000017913355,0.7559618,0.000023068782,0.07524369,0.000045109184,0.000055542856],"about_ca_topic_score_codex":0.00032911345,"about_ca_topic_score_gemma":0.000092155395,"teacher_disagreement_score":0.8044328,"about_ca_system_score_codex":0.0000124425,"about_ca_system_score_gemma":0.00008446157,"threshold_uncertainty_score":0.30577198},"labels":[],"label_agreement":null},{"id":"W2017014583","doi":"10.1016/j.csda.2007.01.007","title":"Building a robust linear model with forward selection and stepwise procedures","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Selection (genetic algorithm); Model selection; Linear model; Mathematics; Computer science; Mathematical optimization; Statistics; Artificial intelligence","score_opus":0.12767640631354232,"score_gpt":0.43707936783523854,"score_spread":0.3094029615216962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017014583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035906082,0.00003111906,0.9938704,0.000039300794,0.000010542644,0.00017491868,0.002185273,0.000057321948,0.000040523304],"genre_scores_gemma":[0.093597434,0.00001033753,0.90533656,0.000054557888,0.00004185957,0.0000063607754,0.00085591234,0.000027136208,0.00006984341],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816585,0.000050173043,0.0004479599,0.0005713493,0.00047306274,0.0002915977],"domain_scores_gemma":[0.997107,0.0018241098,0.00021749528,0.00029308713,0.00038187642,0.00017640369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007676,0.00020729644,0.00038854455,0.00025622055,0.00023176523,0.00006525104,0.00018880465,0.00005563061,0.000024190222],"category_scores_gemma":[0.0011609962,0.0001788962,0.000032412798,0.0006856238,0.0000902461,0.00022508117,0.00014408636,0.00015859149,0.0000015483442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009165087,0.000070163806,0.00054686493,0.00007641315,0.00052854273,0.000009953266,0.000067940906,0.66588044,0.0000086379505,0.32420918,0.0005032337,0.0080069695],"study_design_scores_gemma":[0.00019426692,0.000040212235,0.0006253885,0.0000117248655,0.0009949452,0.000006117759,0.000013075863,0.6176097,0.0000033076774,0.38032338,0.000032721542,0.00014516915],"about_ca_topic_score_codex":0.000044655837,"about_ca_topic_score_gemma":0.0007884494,"teacher_disagreement_score":0.09000683,"about_ca_system_score_codex":0.00005457949,"about_ca_system_score_gemma":0.00011642285,"threshold_uncertainty_score":0.7295175},"labels":[],"label_agreement":null},{"id":"W2018905040","doi":"10.1016/j.csda.2010.05.019","title":"Model-based classification via mixtures of multivariate -distributions","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Initialization; Covariance; Multivariate statistics; Expectation–maximization algorithm; Mathematics; Convergence (economics); Mixture model; Multivariate normal distribution; Maximization; Pattern recognition (psychology); Algorithm; Computer science; Artificial intelligence; Statistics; Mathematical optimization; Maximum likelihood","score_opus":0.05214006332080729,"score_gpt":0.34818186668338064,"score_spread":0.29604180336257335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018905040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023084659,0.000017089931,0.9943468,0.0003142799,0.000102836224,0.00009264638,0.004776102,0.000049163817,0.00007024802],"genre_scores_gemma":[0.39508894,0.000001395254,0.5990223,0.000056980087,0.00001721511,0.0000045150955,0.005793007,0.000004613574,0.000010997862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982041,0.00012791989,0.00047533284,0.0005764121,0.0004310753,0.00018514621],"domain_scores_gemma":[0.99717045,0.00052414206,0.0003162218,0.0013298163,0.0005374912,0.00012189545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006173932,0.00015599756,0.00029487,0.0002833882,0.00017390253,0.00010817052,0.0012644846,0.000083740655,0.000030312558],"category_scores_gemma":[0.00025260902,0.00015150475,0.00009323906,0.0011383344,0.00011900841,0.00029130912,0.00025121408,0.00020874965,0.000006643281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004842478,0.00015379155,0.00033934598,0.000013361889,0.00029150653,0.0000021022395,0.00004070129,0.12508751,0.0019775813,0.8320449,0.0012213785,0.038822997],"study_design_scores_gemma":[0.00013732453,0.0000076149454,0.009662473,0.000001908821,0.0003081012,7.6037446e-7,2.5163172e-7,0.7616818,0.00008304133,0.22787513,0.0001205824,0.00012100118],"about_ca_topic_score_codex":0.0001347925,"about_ca_topic_score_gemma":0.00012820367,"teacher_disagreement_score":0.6365943,"about_ca_system_score_codex":0.000019108202,"about_ca_system_score_gemma":0.00023870215,"threshold_uncertainty_score":0.6178184},"labels":[],"label_agreement":null},{"id":"W2019635779","doi":"10.1016/j.csda.2008.08.014","title":"Modelling small area counts in the presence of overdispersion and spatial autocorrelation","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":120,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Leverhulme Trust","keywords":"Overdispersion; Spatial analysis; Inference; Econometrics; Cluster analysis; Autocorrelation; Statistics; Scale (ratio); Spatial ecology; Mathematics; Computer science; Count data; Geography; Artificial intelligence; Ecology; Cartography","score_opus":0.11873918163305065,"score_gpt":0.25340254549894153,"score_spread":0.1346633638658909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019635779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014402654,0.0001660733,0.9793935,0.00006836435,0.000025122454,0.000053519034,0.0054453425,0.0000030660826,0.00044235412],"genre_scores_gemma":[0.9687067,0.0002017877,0.022789547,0.00003667759,0.000018690289,0.0000022256731,0.008188736,0.0000034575226,0.00005214198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992446,0.000022153123,0.00033789637,0.00023121438,0.000092606446,0.000071560324],"domain_scores_gemma":[0.99922794,0.00025412385,0.00018389548,0.00026255488,0.000051809166,0.000019697804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032205862,0.000062325926,0.00019862966,0.00020981807,0.0000738992,0.000023081022,0.00021462537,0.000028034568,0.00019584391],"category_scores_gemma":[0.00009184741,0.000058520436,0.00003142526,0.0004625783,0.00005391592,0.00009820431,0.000068515525,0.000060735234,0.000028865441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068813124,0.000040768533,0.19256386,0.000008639662,0.00017527891,0.000004512259,0.0003020921,0.77778107,1.1840511e-7,0.026414378,0.0018829443,0.00081947475],"study_design_scores_gemma":[0.00007891405,0.0000052756345,0.1183346,0.000002324209,0.0000846555,9.613484e-7,0.000009031939,0.86675197,5.2542955e-8,0.013903212,0.00077256846,0.000056460216],"about_ca_topic_score_codex":0.007158663,"about_ca_topic_score_gemma":0.00035406594,"teacher_disagreement_score":0.95660394,"about_ca_system_score_codex":0.000012981442,"about_ca_system_score_gemma":0.000015162898,"threshold_uncertainty_score":0.99945277},"labels":[],"label_agreement":null},{"id":"W2020357043","doi":"10.1016/j.csda.2008.06.015","title":"A method for bias-reduction of sample-based MLE of the autologistic model","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Statistics; Mathematics; Row; Sample size determination; Population; Sample (material); Confidence interval; Cluster (spacecraft); Coverage probability; Mean squared error; Computer science; Physics","score_opus":0.3315027015479352,"score_gpt":0.4586701654503985,"score_spread":0.1271674639024633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020357043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000509381,0.000010906313,0.9650561,0.00007722508,0.000039216186,0.00022031883,0.034057062,0.000014665027,0.000015128011],"genre_scores_gemma":[0.089587465,0.0000030136398,0.9086313,0.000021206934,0.000016918255,0.000015617665,0.0016987256,0.000011953157,0.000013772105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803,0.00026587333,0.0007410014,0.00034430873,0.00045961703,0.0001592015],"domain_scores_gemma":[0.9865848,0.011450289,0.0006170777,0.0006772578,0.0006183441,0.000052268657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079291844,0.00014635365,0.0005551155,0.0001735397,0.00016015342,0.000011751555,0.00049803266,0.000056717527,0.000067263645],"category_scores_gemma":[0.0077562877,0.00011145201,0.00015349923,0.00079042953,0.0002980321,0.00004915101,0.00012310263,0.00008611028,5.530456e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053469794,0.00019097769,0.0013056524,0.00018671247,0.00059963734,6.797056e-7,0.000099885016,0.20919421,0.000028801038,0.77784157,0.0027832987,0.0077151004],"study_design_scores_gemma":[0.0001626973,0.000020445268,0.0019540763,0.000008187379,0.0010323556,0.0000013273235,0.0000056174067,0.5292991,0.00003970815,0.46740344,0.00001064319,0.000062388164],"about_ca_topic_score_codex":0.00028372783,"about_ca_topic_score_gemma":0.0000422713,"teacher_disagreement_score":0.32010487,"about_ca_system_score_codex":0.000029939727,"about_ca_system_score_gemma":0.0003165649,"threshold_uncertainty_score":0.92855614},"labels":[],"label_agreement":null},{"id":"W2021096263","doi":"10.1016/j.csda.2010.10.025","title":"Robust likelihood inference for regression parameters in partially linear models","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Central University; Cathay General Hospital; National Science Council","keywords":"Inference; Mathematics; Linear regression; Statistics; Robust regression; Linear model; Generalized linear model; Regression; Bayesian multivariate linear regression; Regression analysis; Econometrics; Computer science; Artificial intelligence","score_opus":0.25928152037565105,"score_gpt":0.46174467960003657,"score_spread":0.2024631592243855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021096263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031546887,0.000012991482,0.98687166,0.000097815595,0.00010272497,0.00029814945,0.0093933605,0.000038723243,0.0000298963],"genre_scores_gemma":[0.09189835,0.000015688325,0.90256,0.000073577416,0.000046505185,0.000044507553,0.0053096525,0.000026436244,0.000025303336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976399,0.00012505958,0.0007367046,0.0006940445,0.00043448707,0.00036983402],"domain_scores_gemma":[0.99167085,0.0067200083,0.00028311744,0.00076787616,0.00037855477,0.00017959937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009588357,0.00023871686,0.00055122736,0.00026318332,0.00014298067,0.00007126667,0.000509632,0.00010904134,0.000052078336],"category_scores_gemma":[0.00454482,0.00021474334,0.00008639429,0.0005833278,0.00011178009,0.0003054508,0.00023120096,0.0003154821,0.0000046923174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042429514,0.0001576747,0.00037864264,0.000046338107,0.00021959226,0.0000080595455,0.000087757624,0.57776105,0.000013349688,0.40413973,0.00073801354,0.01640732],"study_design_scores_gemma":[0.00022875155,0.000018373548,0.0003240222,0.000010479699,0.00034820466,4.4123962e-7,0.0000063900807,0.5108334,0.0000043359837,0.48802736,0.00006417527,0.00013409578],"about_ca_topic_score_codex":0.00011572388,"about_ca_topic_score_gemma":0.002320938,"teacher_disagreement_score":0.088743664,"about_ca_system_score_codex":0.000030153074,"about_ca_system_score_gemma":0.00014546505,"threshold_uncertainty_score":0.8756979},"labels":[],"label_agreement":null},{"id":"W2025162236","doi":"10.1016/j.csda.2006.03.010","title":"New criteria for robust integer-valued designs in linear models","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Integer (computer science); Generalized linear model; Mathematical optimization; Applied mathematics; Algorithm; Computer science; Statistics","score_opus":0.4267899798828539,"score_gpt":0.5165879401463285,"score_spread":0.08979796026347459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025162236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002738535,0.00011938381,0.99278635,0.00011469304,0.00015502553,0.00026543895,0.0060460223,0.000027023949,0.00021219441],"genre_scores_gemma":[0.03408457,0.0000025631032,0.9569024,0.00011123475,0.00012508433,0.000014685253,0.008030378,0.00002117609,0.0007079501],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956281,0.0004908618,0.0012590208,0.0010125788,0.0012889626,0.00032043256],"domain_scores_gemma":[0.9936987,0.004331622,0.00033586784,0.0009272094,0.0005577738,0.00014880237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034138868,0.00023239337,0.00061431754,0.000896977,0.00014612993,0.0004431627,0.0013733042,0.00007702971,0.0007232089],"category_scores_gemma":[0.0018802978,0.00021467208,0.00014056514,0.0025566595,0.000089647576,0.00069124316,0.00036324584,0.00011529628,0.0000656111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000603095,0.00008516601,0.00063705683,0.0000030082913,0.000120983466,0.000007846986,0.00006108424,0.8968484,0.000048808608,0.037593905,0.057745434,0.0067880163],"study_design_scores_gemma":[0.0003278907,0.000028842998,0.0029071297,0.0000032976716,0.0001862177,9.416228e-7,0.00003084646,0.6714126,0.000011511819,0.32455963,0.00037083207,0.00016023629],"about_ca_topic_score_codex":0.0019685833,"about_ca_topic_score_gemma":0.0005875235,"teacher_disagreement_score":0.28696573,"about_ca_system_score_codex":0.000107332184,"about_ca_system_score_gemma":0.0002533052,"threshold_uncertainty_score":0.87540734},"labels":[],"label_agreement":null},{"id":"W2027737251","doi":"10.1016/j.csda.2012.03.025","title":"Hybrid censoring: Models, inferential results and applications","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":243,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Computer science; Econometrics; Mathematics","score_opus":0.17733084859810852,"score_gpt":0.4040035739452627,"score_spread":0.22667272534715419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027737251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003785285,0.00005849441,0.94687206,0.00013930364,0.00002622273,0.00022016253,0.05158101,0.000086745335,0.0006374615],"genre_scores_gemma":[0.558625,0.000030854873,0.39760205,0.000055539378,0.0001031059,0.00005220399,0.0434437,0.000012789219,0.00007479572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982025,0.000073585004,0.0006073321,0.00041904574,0.00042079945,0.000276753],"domain_scores_gemma":[0.99709165,0.0014290077,0.00023927793,0.0006709408,0.00029303323,0.00027606275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003987366,0.00017503444,0.00028222855,0.00017915269,0.00031847483,0.00011025541,0.00028554435,0.000040406296,0.000179548],"category_scores_gemma":[0.0006098466,0.00018232135,0.000045541638,0.0005499266,0.00013533722,0.00034086785,0.00024399404,0.0001234613,0.00007014196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008387531,0.00019274675,0.00031509376,0.000026923703,0.00033102187,4.8409174e-7,0.00003564634,0.005420047,7.9808865e-7,0.9748991,0.013807165,0.0049625933],"study_design_scores_gemma":[0.0002379652,0.000004054006,0.011538257,0.0000029139685,0.0009581582,0.0000034164666,0.0000103079155,0.56490093,0.0000013593267,0.4182849,0.0039028788,0.00015482202],"about_ca_topic_score_codex":0.000059621147,"about_ca_topic_score_gemma":0.000017127912,"teacher_disagreement_score":0.5594809,"about_ca_system_score_codex":0.00004548177,"about_ca_system_score_gemma":0.00004854998,"threshold_uncertainty_score":0.7434849},"labels":[],"label_agreement":null},{"id":"W2028203539","doi":"10.1016/j.csda.2007.10.005","title":"Exact likelihood inference for two exponential populations under joint Type-II censoring","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Mathematics; Statistics; Confidence interval; Estimator; Inference; Exponential distribution; Coverage probability; Exponential function; Exact statistics; Applied mathematics; Computer science","score_opus":0.24565992427178193,"score_gpt":0.4678217453259685,"score_spread":0.22216182105418655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028203539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027098448,0.000012669305,0.97956306,0.00023567304,0.00011502214,0.00030642317,0.016800994,0.00009818181,0.00015812519],"genre_scores_gemma":[0.4763737,0.0000018377378,0.4928282,0.000069133705,0.00006971145,0.000014455166,0.030574268,0.0000139214835,0.000054796503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775875,0.000048629645,0.0008342535,0.0005089564,0.00049847993,0.00035095838],"domain_scores_gemma":[0.99605167,0.0020074425,0.00032251314,0.00062455947,0.0007849782,0.00020881306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068064564,0.00020385218,0.00034839154,0.0002831578,0.0006681993,0.0001120908,0.00032228298,0.000058799866,0.00072089856],"category_scores_gemma":[0.0021149274,0.0002166846,0.00009647732,0.0010788064,0.00009689229,0.00017937794,0.00020765289,0.00012717828,0.000053492335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016250155,0.00022040203,0.00040748186,0.000023990278,0.00037212545,0.0000014822128,0.000045895016,0.020233164,0.000031486834,0.9675092,0.0073996405,0.0037388809],"study_design_scores_gemma":[0.00034625476,0.000019546043,0.04026651,0.0000071215877,0.0009888732,0.0000012361177,0.000025430776,0.48502976,0.000010949923,0.4726661,0.0004503354,0.00018785917],"about_ca_topic_score_codex":0.000119704324,"about_ca_topic_score_gemma":0.00038116684,"teacher_disagreement_score":0.4948431,"about_ca_system_score_codex":0.00011373073,"about_ca_system_score_gemma":0.00011717374,"threshold_uncertainty_score":0.8836141},"labels":[],"label_agreement":null},{"id":"W2029217165","doi":"10.1016/j.csda.2014.09.006","title":"Clustering with the multivariate normal inverse Gaussian distribution","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Science Foundation Ireland","keywords":"Mathematics; Inverse Gaussian distribution; Mixture model; Normal-inverse Gaussian distribution; Multivariate normal distribution; Univariate; Gaussian; Generalized inverse Gaussian distribution; Statistics; Cluster analysis; Normal distribution; Bayesian information criterion; Multivariate statistics; Mixture distribution; Covariance; Applied mathematics; Gaussian random field; Gaussian process; Distribution (mathematics); Probability density function; Mathematical analysis","score_opus":0.02441071631197747,"score_gpt":0.2880331788376962,"score_spread":0.26362246252571875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029217165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008611817,0.000008240526,0.997566,0.00088483375,0.000055052642,0.00007476995,0.0011528146,0.000045690696,0.00012648429],"genre_scores_gemma":[0.17018,0.0000023532955,0.8251161,0.00031479934,0.000053601376,0.0000043627833,0.0042793704,0.000006010198,0.00004340551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983581,0.0002829209,0.00023539236,0.0004942203,0.0004076669,0.00022171269],"domain_scores_gemma":[0.9981121,0.00048846775,0.00017253157,0.0009627922,0.00016128659,0.000102844235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080336677,0.0001510609,0.00021181634,0.00008765271,0.00033805508,0.00030525218,0.0011214701,0.000033150736,0.00001824549],"category_scores_gemma":[0.000092636976,0.000102043035,0.0000432075,0.00091481506,0.000085533655,0.00040508955,0.0005536236,0.00013665146,0.000017149545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018810033,0.00006350973,0.0009538177,0.000017739672,0.00085719867,0.000015014463,0.00033702332,0.33584172,0.00000570416,0.51974726,0.009915096,0.13222711],"study_design_scores_gemma":[0.0002010404,0.000022989969,0.021965612,0.000004064371,0.00034785477,0.00000473066,0.0000031297013,0.9583609,0.0000012942414,0.016635846,0.002303387,0.00014914607],"about_ca_topic_score_codex":0.00027283205,"about_ca_topic_score_gemma":0.0005234349,"teacher_disagreement_score":0.6225192,"about_ca_system_score_codex":0.00003145169,"about_ca_system_score_gemma":0.000061558465,"threshold_uncertainty_score":0.41611943},"labels":[],"label_agreement":null},{"id":"W2029302922","doi":"10.1016/j.csda.2009.03.002","title":"Group sequential testing of homogeneity in genetic linkage analysis","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linkage (software); Homogeneity (statistics); Sample size determination; Genetic linkage; Statistics; Multiple comparisons problem; Monte Carlo method; Mathematics; Computer science; Genetics; Biology; Gene","score_opus":0.5488176037055619,"score_gpt":0.549484249912318,"score_spread":0.0006666462067561607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029302922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031652898,0.00005135943,0.95822054,0.000045371256,0.000059394795,0.00020197267,0.0096455505,0.000039737086,0.000083148014],"genre_scores_gemma":[0.33394155,0.000011817558,0.664418,0.000057281846,0.000067055626,0.0000036084807,0.0014813547,0.000011798173,0.000007575686],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994653,0.0010015769,0.0021710207,0.000877207,0.00093707134,0.00036011921],"domain_scores_gemma":[0.96492064,0.03241389,0.00084188604,0.0012117198,0.00044480726,0.00016708393],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031152472,0.00027962166,0.0014758557,0.0009830093,0.00009605651,0.00007265445,0.00088087446,0.0001383099,0.00036512286],"category_scores_gemma":[0.039778396,0.00028626263,0.0002729283,0.0062312805,0.00018766588,0.00010825463,0.00029419526,0.00027735846,0.000009029894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015998168,0.0022287357,0.29680628,0.0002460031,0.016199615,0.00027586662,0.00017640418,0.28455085,0.00015684059,0.2798186,0.0014754678,0.11790539],"study_design_scores_gemma":[0.00025337335,0.000044463774,0.24439915,0.00000928391,0.00646364,6.7808674e-7,0.0000033316492,0.33502406,0.000004093405,0.41365412,0.0000048024385,0.00013900359],"about_ca_topic_score_codex":0.00041380184,"about_ca_topic_score_gemma":0.0005078972,"teacher_disagreement_score":0.30228865,"about_ca_system_score_codex":0.00007750906,"about_ca_system_score_gemma":0.00010909232,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W2030282746","doi":"10.1016/s0167-9473(02)00103-2","title":"A Monte Carlo study of the accuracy and robustness of ten bivariate location estimators","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bivariate analysis; Monte Carlo method; Estimator; Robustness (evolution); Statistics; Mathematics; Econometrics; Computer science; Applied mathematics","score_opus":0.13878131625680895,"score_gpt":0.43604909307219397,"score_spread":0.297267776815385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030282746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06335915,0.000037770456,0.93440425,0.000013919418,0.000037524587,0.00026069192,0.0018677549,0.000007784103,0.00001117082],"genre_scores_gemma":[0.4998381,0.0000038552803,0.5000689,0.0000035640473,0.000003924474,0.000004828872,0.00006009352,0.000007414104,0.000009335494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980984,0.00035826256,0.0006404992,0.0003368467,0.00044245087,0.00012355397],"domain_scores_gemma":[0.99467206,0.003563374,0.00051967433,0.0006819065,0.0005050957,0.00005786647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063711783,0.00014225833,0.0004564336,0.00012865449,0.00011566178,0.000022378428,0.00030553679,0.00003205823,0.000018378629],"category_scores_gemma":[0.0057128463,0.00010705725,0.0000364028,0.0009036926,0.00012465792,0.00012037679,0.00018713354,0.000090312824,2.2110696e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014450717,0.00039923564,0.007753057,0.00011137965,0.0008941068,0.0000016015504,0.00037536852,0.8106301,0.0000020094974,0.17631374,0.00017590354,0.0033290817],"study_design_scores_gemma":[0.00033768106,0.00003742215,0.026678085,0.00001490469,0.001902471,0.0000012597606,0.00017176806,0.7951909,0.000002719036,0.17555775,0.000008049394,0.00009700712],"about_ca_topic_score_codex":0.00023829068,"about_ca_topic_score_gemma":0.00019078332,"teacher_disagreement_score":0.43647894,"about_ca_system_score_codex":0.000018884542,"about_ca_system_score_gemma":0.000086037195,"threshold_uncertainty_score":0.6839223},"labels":[],"label_agreement":null},{"id":"W2030375608","doi":"10.1016/j.csda.2013.05.015","title":"A hierarchical Bayes model for biomarker subset effects in clinical trials","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Bayes' theorem; Biomarker; Bayes factor; Bayesian probability; Statistics; Computer science; Mathematics; Econometrics; Computational biology; Artificial intelligence; Medicine; Biology; Genetics","score_opus":0.7677535222997305,"score_gpt":0.6494448756109211,"score_spread":0.11830864668880936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030375608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017617152,0.000033433473,0.9759405,0.00044638594,0.00024655467,0.0015962564,0.01988255,0.00005911796,0.0000334799],"genre_scores_gemma":[0.031107485,0.000025930853,0.9637155,0.00038557994,0.0001951473,0.00027898658,0.0041606417,0.00004809044,0.00008266107],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.987754,0.005215692,0.0044844593,0.0012195962,0.00080517196,0.00052106543],"domain_scores_gemma":[0.6251937,0.3719737,0.00090102875,0.0011208869,0.0004740923,0.0003365759],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025118202,0.00036578134,0.0026121899,0.00048145425,0.00012664769,0.00020687621,0.0009668024,0.0002902574,0.00048682626],"category_scores_gemma":[0.41732585,0.00031256158,0.0005358726,0.0010783757,0.00034416528,0.00020654043,0.00047034203,0.00042365523,0.000067733155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004327577,0.0014624981,0.011219104,0.00044622415,0.0057513965,0.000026565336,0.000081278224,0.017787647,0.000008395764,0.6492281,0.14416787,0.16938816],"study_design_scores_gemma":[0.0010548431,0.00003784103,0.018461348,0.000017616618,0.001616369,3.8612433e-7,0.0000021149128,0.49133468,3.6278675e-7,0.48726267,0.000036285048,0.00017548409],"about_ca_topic_score_codex":0.00009998612,"about_ca_topic_score_gemma":0.00014519517,"teacher_disagreement_score":0.47354704,"about_ca_system_score_codex":0.00006557824,"about_ca_system_score_gemma":0.00023862533,"threshold_uncertainty_score":0.99993265},"labels":[],"label_agreement":null},{"id":"W2033317193","doi":"10.1016/j.csda.2007.03.027","title":"Covariance miss-specification and the local influence approach in sensitivity analyses of longitudinal data with drop-outs","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Covariance; Sensitivity (control systems); Drop (telecommunication); Mathematics; Drop out; Econometrics; Statistics; Longitudinal data; Computer science; Data mining; Engineering; Economics","score_opus":0.17932447230720955,"score_gpt":0.43589605519466423,"score_spread":0.2565715828874547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033317193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035792596,0.00010640773,0.9915279,0.000053965232,0.000010749236,0.00018518801,0.004465522,0.0000117334675,0.000059262537],"genre_scores_gemma":[0.4504845,0.00001671136,0.547514,0.000011457728,0.000013246715,0.0000017691196,0.0019504132,0.000006185986,0.0000016990381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730676,0.00042263247,0.00074215926,0.0006839698,0.0006226214,0.00022188219],"domain_scores_gemma":[0.9886424,0.009177705,0.00044184385,0.0012512131,0.0004013965,0.00008544736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003648509,0.00019081242,0.00060587586,0.00022848656,0.00011863342,0.0000794279,0.0005553789,0.000047116566,0.000019154513],"category_scores_gemma":[0.0022251152,0.00013340103,0.000026598658,0.0014474468,0.0009223896,0.00024263219,0.00038373543,0.00021745288,0.000001749852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044202255,0.0003061846,0.048393086,0.00020234514,0.0010352167,0.000048144528,0.00022002759,0.02042066,0.000016351765,0.88418525,0.00027939084,0.044451304],"study_design_scores_gemma":[0.0004174129,0.00001109957,0.26339298,0.00001990078,0.00092535827,0.000008655432,0.000056913323,0.5857561,0.0000033548913,0.14928594,0.000008609393,0.00011363983],"about_ca_topic_score_codex":0.0009171653,"about_ca_topic_score_gemma":0.00089301285,"teacher_disagreement_score":0.73489934,"about_ca_system_score_codex":0.00003426604,"about_ca_system_score_gemma":0.000106337684,"threshold_uncertainty_score":0.5439936},"labels":[],"label_agreement":null},{"id":"W2033511646","doi":"10.1016/j.csda.2013.09.011","title":"The effect of the prior distribution in the Bayesian Adjustment for Confounding algorithm","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Confounding; Outcome (game theory); Estimator; Prior probability; Bayesian probability; Mathematics; Econometrics","score_opus":0.0632994742926309,"score_gpt":0.4135541767843135,"score_spread":0.3502547024916826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033511646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001128076,0.000048214846,0.9934658,0.00026033694,0.000042256997,0.00093282235,0.0040923394,0.00001695904,0.000013216055],"genre_scores_gemma":[0.45985988,0.000030579446,0.532751,0.00006113939,0.00005689166,0.00035169168,0.006837985,0.000016032242,0.000034783316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984509,0.00029465352,0.00045203525,0.00021074669,0.0004138675,0.00017783647],"domain_scores_gemma":[0.98938465,0.009387194,0.0003260002,0.00067511323,0.00020361961,0.000023417866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011824132,0.00013131605,0.00024974789,0.000046650803,0.0002770603,0.00008837576,0.00076660584,0.000034388067,0.000022728593],"category_scores_gemma":[0.0017906026,0.000065084954,0.00008084647,0.0005351355,0.00015326838,0.0001241774,0.00017414545,0.00011912218,0.0000021296244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002935372,0.00012876635,0.004183375,0.00014564862,0.0011972494,0.0000014293199,0.00033411462,0.0077862716,0.0000137094075,0.6891048,0.032466892,0.2646084],"study_design_scores_gemma":[0.00016920654,0.000054211214,0.015694687,0.000014411685,0.00063003576,8.680198e-7,0.00004758297,0.5806621,0.00003073802,0.40217942,0.0004436146,0.00007311057],"about_ca_topic_score_codex":0.00017990766,"about_ca_topic_score_gemma":0.00018790427,"teacher_disagreement_score":0.57287586,"about_ca_system_score_codex":0.00009001124,"about_ca_system_score_gemma":0.00004056252,"threshold_uncertainty_score":0.26540875},"labels":[],"label_agreement":null},{"id":"W2035418817","doi":"10.1016/j.csda.2009.10.021","title":"A simulation study comparing methods for calculating confidence intervals for directly standardized rates","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health","funders":"","keywords":"Confidence interval; Coverage probability; Statistics; Robust confidence intervals; CDF-based nonparametric confidence interval; Mathematics; Tolerance interval; Point estimation; Confidence distribution; Credible interval; Variance (accounting)","score_opus":0.31590279170475616,"score_gpt":0.5724191080337716,"score_spread":0.25651631632901545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035418817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016404177,0.000039743154,0.9913672,0.0000521088,0.000071828355,0.0011267036,0.005602941,0.00006809669,0.000030931926],"genre_scores_gemma":[0.32332185,0.0000010612143,0.674565,0.00005305071,0.0000452503,0.00004405645,0.0019404289,0.000015031652,0.00001424173],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692965,0.0005666496,0.0010749216,0.00070672535,0.00040750642,0.00031456738],"domain_scores_gemma":[0.9610144,0.036669005,0.0004935317,0.00057526724,0.0011283576,0.000119460936],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0036465712,0.00026523377,0.0009716193,0.0002511914,0.00035177867,0.0002644791,0.0004578378,0.00005372839,0.000063555955],"category_scores_gemma":[0.025261022,0.00025161996,0.00014997942,0.0006761356,0.00006157698,0.00016952217,0.0001293252,0.00011122327,0.0000013678373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029862684,0.00055853825,0.0025739754,0.00013764712,0.00230231,0.0000028485842,0.00066524406,0.44959038,0.00003746353,0.39735293,0.0009353207,0.14554471],"study_design_scores_gemma":[0.0006130354,0.00015215261,0.005541152,0.000016356655,0.0017011219,1.9435019e-7,0.000047508314,0.5656512,0.0000075809116,0.42603427,0.00006810439,0.0001673699],"about_ca_topic_score_codex":0.000072475916,"about_ca_topic_score_gemma":0.00006753365,"teacher_disagreement_score":0.32168144,"about_ca_system_score_codex":0.00007517592,"about_ca_system_score_gemma":0.00008847227,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W2037360823","doi":"10.1016/j.csda.2010.07.009","title":"Simulation smoothing for state–space models: A computational efficiency analysis","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Smoothing; State space; Cholesky decomposition; Gaussian; Kalman filter; Algorithm; Mathematics; Mathematical optimization; Applied mathematics; Computer science; Statistics","score_opus":0.061005219233886,"score_gpt":0.3427019538957092,"score_spread":0.28169673466182316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037360823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019606156,0.0000354193,0.9930875,0.0003134542,0.0001544303,0.00021417675,0.0040168157,0.000171305,0.000046286965],"genre_scores_gemma":[0.49052256,0.0000020535874,0.5029975,0.00011112238,0.000031274867,0.000010208168,0.0062847054,0.000009577678,0.000030997424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650645,0.000105051295,0.0007736554,0.0012283061,0.0009541873,0.00043236712],"domain_scores_gemma":[0.99422616,0.0026793117,0.00042082023,0.0012271117,0.0012148201,0.000231797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010667832,0.0003072941,0.00055050233,0.0010532849,0.0005341678,0.0007591669,0.0017615512,0.0000998499,0.00004990229],"category_scores_gemma":[0.00045149802,0.00032482555,0.0002397083,0.0039394195,0.000116858515,0.0010757426,0.00047742916,0.00030480215,0.000016317143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007684851,0.000096248106,0.0005187297,0.000009949588,0.0013808825,0.0000027907547,0.00025251787,0.8301308,0.0000037656416,0.16110653,0.00031579193,0.006174295],"study_design_scores_gemma":[0.00021658138,0.000021868298,0.0021129844,0.0000026548564,0.0014643884,7.6684444e-7,0.0000050859144,0.741486,8.8264875e-7,0.2542991,0.00010490736,0.00028476375],"about_ca_topic_score_codex":0.0003090807,"about_ca_topic_score_gemma":0.00042889756,"teacher_disagreement_score":0.49009,"about_ca_system_score_codex":0.000052026524,"about_ca_system_score_gemma":0.0003278887,"threshold_uncertainty_score":0.99992037},"labels":[],"label_agreement":null},{"id":"W2037740528","doi":"10.1016/j.csda.2012.12.012","title":"Simulation-based Bayesian inference for epidemic models","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Medical Research Council; Biotechnology and Biological Sciences Research Council","keywords":"Markov chain Monte Carlo; Computer science; Missing data; Bayesian inference; Inference; Bayesian probability; Reversible-jump Markov chain Monte Carlo; Monte Carlo method; Marginal likelihood; Sampling (signal processing); Posterior probability; Algorithm; Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.17149250930281654,"score_gpt":0.4445010993073115,"score_spread":0.27300859000449496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037740528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000607543,0.000015157049,0.9875142,0.00020131233,0.000049373604,0.00048694274,0.011525795,0.000071649934,0.00007480598],"genre_scores_gemma":[0.2875676,0.0000016484258,0.7062393,0.00018014459,0.000043963995,0.000069195325,0.0058534513,0.000020902997,0.0000238131],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974355,0.00020930612,0.0008392292,0.0006658646,0.0004959759,0.00035411475],"domain_scores_gemma":[0.95550877,0.042213954,0.0003423672,0.00083701656,0.00089845713,0.00019944148],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00068589783,0.00026116837,0.00059514656,0.00029269984,0.00023491165,0.00020333468,0.0006163679,0.00009015433,0.0010277132],"category_scores_gemma":[0.011344832,0.00024693133,0.000117531104,0.0007557342,0.0001264474,0.0003487396,0.00013601762,0.00013839675,0.000041401356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067011724,0.00006197464,0.0006710268,0.00005368752,0.00030279922,9.511863e-7,0.00002103597,0.5541237,6.8934537e-7,0.4273169,0.0024017456,0.015038747],"study_design_scores_gemma":[0.0001537183,0.000016650798,0.0009337832,0.000008453276,0.0005915598,6.5206486e-8,0.000004058711,0.5026183,4.0619636e-7,0.49548125,0.00003888457,0.00015283423],"about_ca_topic_score_codex":0.00031614522,"about_ca_topic_score_gemma":0.000084407744,"teacher_disagreement_score":0.28750682,"about_ca_system_score_codex":0.0000575461,"about_ca_system_score_gemma":0.00019060803,"threshold_uncertainty_score":0.9999983},"labels":[],"label_agreement":null},{"id":"W2042326417","doi":"10.1016/j.csda.2010.07.019","title":"Special issue on variable selection and robust procedures","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lasso (programming language); Computer science; Context (archaeology); Principal component analysis; Process (computing); Data mining; Feature selection; Statistical process control; Fault detection and isolation; Projection pursuit; Selection (genetic algorithm); Multivariate statistics; Variable (mathematics); Machine learning; Artificial intelligence; Mathematics","score_opus":0.08844160381691557,"score_gpt":0.41043960390459194,"score_spread":0.3219980000876764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042326417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035178987,0.0000037159477,0.9938561,0.000081197475,0.00017937362,0.0001294731,0.004165715,0.000039891933,0.0011927834],"genre_scores_gemma":[0.0023097026,0.0000076256006,0.99341255,0.00010540777,0.0017066731,0.0000083813375,0.00208859,0.000020236539,0.00034085778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99844795,0.000076825876,0.0003517258,0.00053953973,0.00037898956,0.00020498075],"domain_scores_gemma":[0.9968892,0.002226916,0.0001548225,0.00034928365,0.0002475863,0.00013224602],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044489958,0.00017489509,0.00033293833,0.00018053492,0.00024400408,0.00010821305,0.00021165672,0.0000708741,0.0010606762],"category_scores_gemma":[0.0032219724,0.00016460188,0.000027105543,0.0005387462,0.00008280934,0.00015055832,0.00012824146,0.0002660959,0.00001783086],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027419583,0.00012102294,0.00024594078,0.00005063533,0.00035579831,0.0000041962694,0.000041928633,0.058407877,0.000012702749,0.8816655,0.041306235,0.017760715],"study_design_scores_gemma":[0.00012366663,0.00002614649,0.0010866226,0.000004291634,0.00054061296,0.0000033109266,0.0000048986612,0.46266437,0.000002006765,0.5293163,0.006105279,0.00012249633],"about_ca_topic_score_codex":0.00005547403,"about_ca_topic_score_gemma":0.0005542914,"teacher_disagreement_score":0.4042565,"about_ca_system_score_codex":0.000020151767,"about_ca_system_score_gemma":0.00008981939,"threshold_uncertainty_score":0.9998525},"labels":[],"label_agreement":null},{"id":"W2047815880","doi":"10.1016/j.csda.2015.03.013","title":"Likelihood inference for small area estimation using data cloning","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Manitoba; Manitoba Health","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Small area estimation; Generalized linear mixed model; Markov chain Monte Carlo; Statistics; Inference; Mathematics; Bayesian probability; Computer science; Econometrics; Sample size determination; Bayesian inference; Algorithm; Artificial intelligence; Estimator","score_opus":0.4510083262298539,"score_gpt":0.4857792121440956,"score_spread":0.03477088591424171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047815880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005562322,0.000037952374,0.96730494,0.00006517053,0.00010760442,0.00024805812,0.03158317,0.000058180143,0.000038676775],"genre_scores_gemma":[0.022611264,0.000004391569,0.9412825,0.000057199464,0.00008342712,0.000010859266,0.03591586,0.000026015876,0.000008497845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734783,0.00018908967,0.0007560112,0.00080529106,0.0005522666,0.00034950383],"domain_scores_gemma":[0.99027807,0.006738638,0.0004273283,0.001498052,0.00079552433,0.00026238203],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001709662,0.00024963758,0.0005570769,0.0002562338,0.00021270798,0.00027711946,0.0011546601,0.0000796863,0.00007421312],"category_scores_gemma":[0.016258158,0.00024602385,0.000050379098,0.0008198968,0.00010546528,0.0003733408,0.00079012266,0.00014709187,0.00001102667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075698816,0.00032343515,0.005557205,0.00023653923,0.0019611164,0.000022501095,0.0003892801,0.07069951,0.0000071941618,0.78686535,0.010056112,0.12380605],"study_design_scores_gemma":[0.000209745,0.000022086251,0.0005830718,0.00001807308,0.0014733345,0.0000019689542,0.000021618722,0.5256336,7.842125e-7,0.4717503,0.00012639127,0.00015907931],"about_ca_topic_score_codex":0.00040045322,"about_ca_topic_score_gemma":0.00038457222,"teacher_disagreement_score":0.45493406,"about_ca_system_score_codex":0.000090011585,"about_ca_system_score_gemma":0.0004645488,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W2047931364","doi":"10.1016/j.csda.2009.10.001","title":"Exact optimal inference in regression models under heteroskedasticity and non-normality of unknown form","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Heteroscedasticity; Mathematics; Inference; Normality; Econometrics; Statistics; Regression analysis; Regression; Applied mathematics; Computer science; Artificial intelligence","score_opus":0.161607443407036,"score_gpt":0.4636711159213311,"score_spread":0.3020636725142951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047931364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0277406,0.000029890936,0.9689514,0.000039246494,0.000014275031,0.00013109508,0.0030124118,0.000014120641,0.00006695186],"genre_scores_gemma":[0.49079484,0.000026080366,0.50839704,0.000027721519,0.000006103678,0.0000017327468,0.0007340027,0.0000050080316,0.000007469954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979984,0.00012949451,0.0007239856,0.0004842656,0.00042196526,0.00024187847],"domain_scores_gemma":[0.9956652,0.0031807646,0.00030720956,0.00048511848,0.00023629745,0.0001254275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061716075,0.00020641873,0.00061565003,0.00022149696,0.00008564301,0.00003972619,0.00027468445,0.00007016726,0.00002662423],"category_scores_gemma":[0.0010768966,0.00018132165,0.000048301365,0.00050646666,0.00012990886,0.00039521948,0.00022129768,0.00017425341,6.348778e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052273906,0.00021313582,0.0006291295,0.00006730998,0.00015382929,0.00000796104,0.0001386528,0.5226723,0.000015133263,0.4575815,0.000072534196,0.018396266],"study_design_scores_gemma":[0.00019019327,0.00003521085,0.013114818,0.000023004777,0.00021785976,4.958161e-7,0.000008930584,0.5050981,0.000004052246,0.4812083,0.0000018205394,0.00009720141],"about_ca_topic_score_codex":0.00013435473,"about_ca_topic_score_gemma":0.00012537293,"teacher_disagreement_score":0.46305424,"about_ca_system_score_codex":0.000046391673,"about_ca_system_score_gemma":0.000077088465,"threshold_uncertainty_score":0.73940825},"labels":[],"label_agreement":null},{"id":"W2050334918","doi":"10.1016/j.csda.2010.01.033","title":"A comparative study of robust designs for M-estimated regression models","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Robust regression; Mean squared error; Regression; Regression analysis; Least-squares function approximation; Applied mathematics; Estimator","score_opus":0.6235838049097152,"score_gpt":0.568700766208028,"score_spread":0.0548830387016872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050334918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053290088,0.000029211666,0.9398827,0.000017966855,0.000115399635,0.00052865944,0.0060251015,0.00002167967,0.000089199544],"genre_scores_gemma":[0.46873295,7.037074e-7,0.5294389,0.000010291686,0.000013358142,0.000017141549,0.0017369239,0.000007240747,0.000042495434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955532,0.0005411149,0.0011486128,0.0009039005,0.0016434363,0.00020976557],"domain_scores_gemma":[0.98870856,0.007626456,0.0007321127,0.0012564796,0.0015288604,0.00014754468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032377718,0.00022154255,0.0008452363,0.00066271337,0.00026779075,0.00022918182,0.0014847849,0.00006368041,0.00030604267],"category_scores_gemma":[0.0021927364,0.00017249481,0.00010405819,0.0022078305,0.00018830886,0.0005291486,0.00045333037,0.0001642014,0.000017773613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014110572,0.0007603401,0.0025995648,0.0000038728513,0.0006959644,0.000003827965,0.0011156417,0.9748036,0.00073966425,0.0089564845,0.006682533,0.0034973451],"study_design_scores_gemma":[0.00057451485,0.00020615522,0.011173711,0.0000044268836,0.0007101682,0.0000010178111,0.0006422814,0.9055055,0.00008425339,0.08090133,0.000031577478,0.00016507319],"about_ca_topic_score_codex":0.0002329483,"about_ca_topic_score_gemma":0.00036703618,"teacher_disagreement_score":0.41544285,"about_ca_system_score_codex":0.00002427113,"about_ca_system_score_gemma":0.00013930148,"threshold_uncertainty_score":0.7034134},"labels":[],"label_agreement":null},{"id":"W2050405957","doi":"10.1016/j.csda.2012.05.019","title":"Learned-loss boosting","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Robustification; Boosting (machine learning); Covariate; Spline (mechanical); Regression; Mathematics; Statistics; Regression analysis; Mathematical optimization; Computer science; Econometrics; Artificial intelligence; Machine learning; Engineering","score_opus":0.3353865682554928,"score_gpt":0.5084236974997517,"score_spread":0.1730371292442589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050405957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005649691,0.00010980727,0.99217504,0.00009535047,0.00009334651,0.00009410392,0.0061449287,0.00006992373,0.00065252517],"genre_scores_gemma":[0.12994604,0.00001711369,0.86509186,0.00011903436,0.0001517289,0.000006535026,0.00444808,0.000025522804,0.00019408857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99784195,0.00020942614,0.00053908495,0.00042913697,0.000538441,0.00044193357],"domain_scores_gemma":[0.99384207,0.0047199517,0.0002451179,0.00071735843,0.00022221661,0.0002532856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010900176,0.00020162483,0.0004450367,0.00017573482,0.0002444389,0.00006488715,0.00040498856,0.000055039458,0.00042826607],"category_scores_gemma":[0.0036605361,0.00019339874,0.00007512018,0.0006645846,0.00011049346,0.00035877866,0.00036770495,0.00018815754,0.00006414949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010046917,0.00014695938,0.0062152618,0.000039730512,0.00078656676,0.000009584816,0.000110993424,0.007961055,0.000002026198,0.95152843,0.006200933,0.026988398],"study_design_scores_gemma":[0.00012406809,0.000009054632,0.00356966,0.000005346286,0.0012617627,0.0000040859904,0.000023996769,0.3804405,0.0000014171769,0.61204565,0.0023246445,0.00018982633],"about_ca_topic_score_codex":0.000060758954,"about_ca_topic_score_gemma":0.000034294073,"teacher_disagreement_score":0.37247944,"about_ca_system_score_codex":0.00007279737,"about_ca_system_score_gemma":0.000044726054,"threshold_uncertainty_score":0.7886572},"labels":[],"label_agreement":null},{"id":"W2050427936","doi":"10.1016/j.csda.2012.09.017","title":"A new semiparametric estimation method for accelerated hazards mixture cure model","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Covariate; Semiparametric model; Semiparametric regression; Estimation; Proportional hazards model; Estimating equations; Mathematics; Fraction (chemistry); Accelerated failure time model; Computer science; Hazard; Econometrics; Statistics; Data set; Estimation theory; Applied mathematics; Mathematical optimization; Maximum likelihood; Estimator","score_opus":0.21191886360739928,"score_gpt":0.48067371718276014,"score_spread":0.2687548535753609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050427936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009563888,0.00009919452,0.98330975,0.00015533404,0.0000973616,0.0003253456,0.015754582,0.00007263093,0.00009016766],"genre_scores_gemma":[0.007782125,0.000010931514,0.9785499,0.00016991573,0.0001388122,0.000029864625,0.012977161,0.00003552575,0.00030579217],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974425,0.00022379735,0.0007170295,0.000536006,0.00064009475,0.00044058182],"domain_scores_gemma":[0.99051285,0.007478788,0.00037585833,0.0007059184,0.00058429386,0.0003423187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014768065,0.00028991012,0.00064096146,0.0004678892,0.0002129346,0.000171972,0.0005238534,0.00013735953,0.00037844764],"category_scores_gemma":[0.0073748115,0.00026935924,0.00012120485,0.0020291053,0.000039166807,0.00033487927,0.00020057123,0.00020280085,0.000020212367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026931613,0.00013601752,0.00038704183,0.0000855629,0.000993892,8.2091225e-7,0.00013654279,0.1728537,0.000006263998,0.62694347,0.0973122,0.10111758],"study_design_scores_gemma":[0.00020397565,0.000015695334,0.001005015,0.0000062204863,0.0020119047,0.0000015726494,0.0000044242393,0.5640784,0.000005544738,0.4321461,0.00034119454,0.00017998074],"about_ca_topic_score_codex":0.00013105385,"about_ca_topic_score_gemma":0.000025787796,"teacher_disagreement_score":0.39122468,"about_ca_system_score_codex":0.00008144818,"about_ca_system_score_gemma":0.00028086582,"threshold_uncertainty_score":0.99997586},"labels":[],"label_agreement":null},{"id":"W2050638343","doi":"10.1016/j.csda.2009.02.007","title":"Effects of ignoring baseline on modeling transitions from intact cognition to dementia","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Robert J. Kleberg, Jr. and Helen C. Kleberg Foundation; National Institute on Aging; University of Kentucky","keywords":"Dementia; Cognition; Covariate; Multinomial logistic regression; Baseline (sea); Multinomial distribution; Cohort; Cognitive decline; Psychology; Logistic regression; Markov chain; Medicine; Gerontology; Audiology; Demography; Statistics; Psychiatry; Internal medicine; Mathematics; Disease","score_opus":0.07790374400610788,"score_gpt":0.38888932124822967,"score_spread":0.3109855772421218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050638343","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029028503,0.000021619318,0.98445916,0.00012342268,0.000034484572,0.0001697189,0.012207205,0.000029434863,0.000052130916],"genre_scores_gemma":[0.41204545,0.0000047537046,0.5833444,0.00012351207,0.00003294039,0.0000039722545,0.004437783,0.0000063721573,8.083145e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998205,0.00019734229,0.0005568605,0.00041846343,0.0004565896,0.00016576782],"domain_scores_gemma":[0.9951127,0.003985771,0.00013966043,0.0003592492,0.00027681736,0.00012579933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037925478,0.00016466407,0.00041378874,0.00028162022,0.00011067953,0.000050377424,0.00025103884,0.00004083799,0.00017522008],"category_scores_gemma":[0.0018364311,0.00016596413,0.000068288435,0.00065815717,0.000022643215,0.00009349416,0.00004731821,0.00011144783,0.0000147890305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013495095,0.00095768773,0.000121220364,0.00014048349,0.0028581456,0.000039646555,0.00036570846,0.22333543,0.00053883845,0.6551191,0.0019827536,0.114406],"study_design_scores_gemma":[0.00015742112,0.000055643548,0.0021502299,0.00004629145,0.0023412204,1.532861e-7,0.0000074807185,0.51984054,0.000048533886,0.47525212,0.0000025832683,0.000097769866],"about_ca_topic_score_codex":0.000121645,"about_ca_topic_score_gemma":0.000055821693,"teacher_disagreement_score":0.40914258,"about_ca_system_score_codex":0.000024393854,"about_ca_system_score_gemma":0.000039105547,"threshold_uncertainty_score":0.6767821},"labels":[],"label_agreement":null},{"id":"W2053721748","doi":"10.1016/s0167-9473(02)00206-2","title":"Discriminating between Weibull and generalized exponential distributions","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":178,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Weibull distribution; Mathematics; Logarithm; Statistics; Natural exponential family; Exponential family; Exponential distribution; Exponential function; Applied mathematics; Gamma distribution; Exponentiated Weibull distribution; Sample size determination; Heavy-tailed distribution; Random variable; Mathematical analysis","score_opus":0.16067816764088463,"score_gpt":0.41475244955793045,"score_spread":0.25407428191704584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053721748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004729323,0.00002301276,0.9473194,0.00023354948,0.000026864747,0.00015732033,0.04721657,0.00006748513,0.00022648806],"genre_scores_gemma":[0.47597846,0.000007193937,0.48498058,0.000027179634,0.000026376967,0.000018870174,0.038900487,0.0000104282235,0.000050424635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979693,0.00019795963,0.00062881893,0.00052157865,0.00043141612,0.00025090968],"domain_scores_gemma":[0.9968105,0.0019195379,0.00023937428,0.0005404655,0.00027928993,0.00021085018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045712004,0.0001966668,0.0003784924,0.00015626106,0.00050227495,0.0001660116,0.00025512715,0.000057754725,0.0006904097],"category_scores_gemma":[0.0024933317,0.00020165618,0.000062881874,0.00082500075,0.00018778886,0.0001580044,0.00014987966,0.00013067605,0.00003631079],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000197558,0.00008501204,0.0036142361,0.000021081267,0.0004530092,0.0000021112055,0.000029116214,0.00042094415,0.0000041192516,0.9861999,0.007468012,0.0017004833],"study_design_scores_gemma":[0.00038184735,0.0000100621255,0.070084296,0.000005973302,0.0024677715,0.0000036300817,0.000028482618,0.22388895,0.000008605857,0.70067775,0.002184707,0.00025789562],"about_ca_topic_score_codex":0.00006416623,"about_ca_topic_score_gemma":0.00005689365,"teacher_disagreement_score":0.47124913,"about_ca_system_score_codex":0.000054768116,"about_ca_system_score_gemma":0.00007205233,"threshold_uncertainty_score":0.82233},"labels":[],"label_agreement":null},{"id":"W2054671350","doi":"10.1016/j.csda.2009.11.012","title":"On testing for serial correlation of unknown form using wavelet thresholding","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Wavelet; Mathematics; Estimator; Monte Carlo method; Cascade algorithm; Statistics; Spectral density; Statistical hypothesis testing; Algorithm; Applied mathematics; Wavelet transform; Discrete wavelet transform; Artificial intelligence; Computer science","score_opus":0.097960826011978,"score_gpt":0.3669477939380644,"score_spread":0.26898696792608645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054671350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036175656,0.000016990783,0.9952485,0.000057793237,0.00012905386,0.0001239582,0.00070588535,0.00003231938,0.000067941524],"genre_scores_gemma":[0.21843976,6.5429293e-7,0.77982336,0.00013594811,0.000059577706,9.117622e-7,0.0015230041,0.000005259588,0.000011507682],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838585,0.00008003873,0.0004719122,0.00044065036,0.00042318084,0.00019836226],"domain_scores_gemma":[0.9967139,0.0018985466,0.00033009532,0.0005213776,0.0004797592,0.00005634289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008176113,0.00013766403,0.00030411602,0.00033283117,0.00023806174,0.00017313678,0.0006521765,0.000042948624,0.000007560997],"category_scores_gemma":[0.0009633815,0.00013954753,0.0000699668,0.0012326707,0.000031204825,0.00047144602,0.00013392727,0.00008102187,0.0000018580862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032457458,0.000062822306,0.00020621272,0.000012702568,0.00017815112,0.0000049943505,0.00008510302,0.7190173,0.00026317005,0.20404853,0.0006233729,0.07546517],"study_design_scores_gemma":[0.00033874135,0.00010437073,0.004545902,0.000015380176,0.00029220202,0.000002319561,0.0000014422575,0.7954779,0.000045135526,0.19902766,0.000030307265,0.00011863703],"about_ca_topic_score_codex":0.000053946686,"about_ca_topic_score_gemma":0.0000062796876,"teacher_disagreement_score":0.21542512,"about_ca_system_score_codex":0.00005151768,"about_ca_system_score_gemma":0.00012040051,"threshold_uncertainty_score":0.5690583},"labels":[],"label_agreement":null},{"id":"W2055773936","doi":"10.1016/j.csda.2013.07.020","title":"Linear Bayes estimator for the two-parameter exponential family under type II censoring","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Censoring (clinical trials); Mathematics; Exponential family; Bayes' theorem; Statistics; Estimator; Applied mathematics; Bayesian probability","score_opus":0.17811122387331182,"score_gpt":0.4265613729662296,"score_spread":0.24845014909291777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055773936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017358861,0.000030334257,0.98762625,0.00083782146,0.00011203293,0.00047720072,0.009057567,0.00007450823,0.000048410613],"genre_scores_gemma":[0.26353338,0.0000051984953,0.7222705,0.0002641565,0.00008962717,0.000115152674,0.013555715,0.000020291105,0.0001459736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824274,0.0000634282,0.0005677326,0.00043492307,0.0004388792,0.00025230032],"domain_scores_gemma":[0.9925414,0.0056585353,0.00022425513,0.0006909427,0.00073134096,0.00015353975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002730422,0.00019256839,0.00029732598,0.0001124795,0.0006211419,0.0001899673,0.00050692016,0.00004645258,0.00078640884],"category_scores_gemma":[0.0022218481,0.00015437457,0.00009205932,0.0006856947,0.00014759609,0.00018525883,0.00024235535,0.00011672169,0.00019667397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001175238,0.00013512518,0.0001144942,0.000018829889,0.0008314377,5.114035e-7,0.00003641241,0.08348617,0.000010687531,0.85670674,0.055754177,0.0028936951],"study_design_scores_gemma":[0.00027146537,0.000015575297,0.008423602,0.000003580266,0.0010864371,8.8778205e-7,0.00004264129,0.69884735,0.0000028265374,0.2903296,0.0008403097,0.00013571972],"about_ca_topic_score_codex":0.0002083908,"about_ca_topic_score_gemma":0.00002643627,"teacher_disagreement_score":0.61536115,"about_ca_system_score_codex":0.00005131286,"about_ca_system_score_gemma":0.00009371305,"threshold_uncertainty_score":0.8610625},"labels":[],"label_agreement":null},{"id":"W2057097409","doi":"10.1016/s0167-9473(00)00007-4","title":"Some approximations to the multivariate hypergeometric distribution with applications to hypothesis testing","year":2000,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Differential Equations and Boundary Problems","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hypergeometric distribution; Multivariate statistics; Mathematics; Applied mathematics; Multivariate analysis; Hypergeometric function; Statistical hypothesis testing; Generalized hypergeometric function; Confluent hypergeometric function; Econometrics; Statistics; Mathematical analysis","score_opus":0.1269337313134147,"score_gpt":0.33597439671820684,"score_spread":0.20904066540479213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057097409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057314467,0.000013505993,0.9782511,0.00064572506,0.000014804901,0.00067557715,0.014490848,0.000074016025,0.0001029946],"genre_scores_gemma":[0.17818329,0.000004373192,0.81174827,0.00017395067,0.00012164197,0.00025170937,0.009210484,0.000022749586,0.00028356013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980118,0.00009343768,0.0005079777,0.0005274333,0.000599729,0.0002595748],"domain_scores_gemma":[0.9956604,0.0026951062,0.00015346544,0.00089959835,0.00042458027,0.00016682685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004428201,0.00019710495,0.00029225732,0.00035057878,0.00078594056,0.00035727574,0.0006363622,0.000033462624,0.0003126744],"category_scores_gemma":[0.0009783973,0.0001456014,0.00005054451,0.005307678,0.000056372042,0.00022438657,0.00015326781,0.00010734596,0.0002820625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002644481,0.00059516844,0.0008923661,0.000045537305,0.0015691632,0.0000032565124,0.00024042332,0.5201863,0.00000899773,0.22736363,0.0106602395,0.23840848],"study_design_scores_gemma":[0.000259506,0.00006778191,0.02155381,0.000018115748,0.0024534927,0.000005351741,0.00006759781,0.7319892,0.0000017918034,0.23008344,0.013121669,0.0003782489],"about_ca_topic_score_codex":0.00088068383,"about_ca_topic_score_gemma":0.00054408173,"teacher_disagreement_score":0.23803023,"about_ca_system_score_codex":0.00011847151,"about_ca_system_score_gemma":0.00011614388,"threshold_uncertainty_score":0.60448986},"labels":[],"label_agreement":null},{"id":"W2064453215","doi":"10.1016/s0167-9473(99)00035-3","title":"Estimation of parameters of the half-logistic distribution using generalized ranked set sampling","year":2000,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Estimator; Mathematics; Statistics; Efficiency; Extremum estimator; Sampling (signal processing); M-estimator; Scale (ratio); Set (abstract data type); Computer science","score_opus":0.26418188619675503,"score_gpt":0.43999908565676193,"score_spread":0.1758171994600069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064453215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052863713,0.000014559345,0.9003209,0.0000861009,0.000025939538,0.00022465074,0.04642085,0.000023735669,0.000019544224],"genre_scores_gemma":[0.54616946,0.0000053495555,0.43110904,0.000016874132,0.0000064107735,0.000006283511,0.022667645,0.000007135112,0.000011803194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772584,0.00019083494,0.0009808767,0.0003381713,0.0005927858,0.0001715106],"domain_scores_gemma":[0.9965311,0.0017135164,0.00057522586,0.00075638056,0.00035136176,0.000072381226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043092665,0.0001669753,0.00043452042,0.000093673465,0.00023215746,0.000041117353,0.00046025068,0.00005966316,0.0006025139],"category_scores_gemma":[0.0016392085,0.00014364689,0.00012769336,0.0013723761,0.0003183795,0.00011385795,0.00009593425,0.0000986093,0.000008652534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019376736,0.00012528828,0.00024090451,0.00005984504,0.0004939709,3.096266e-7,0.000038804847,0.63430464,0.000021246266,0.3572221,0.00086711836,0.006606407],"study_design_scores_gemma":[0.00027062686,0.0000077385075,0.011176762,0.000019335695,0.0017807918,0.0000017801859,0.000008775937,0.7980725,0.000036198257,0.1884604,0.00005397889,0.000111086745],"about_ca_topic_score_codex":0.00040621744,"about_ca_topic_score_gemma":0.00003712463,"teacher_disagreement_score":0.49330574,"about_ca_system_score_codex":0.00008045993,"about_ca_system_score_gemma":0.00011586169,"threshold_uncertainty_score":0.65971047},"labels":[],"label_agreement":null},{"id":"W2065015301","doi":"10.1016/j.csda.2009.03.001","title":"Robustness of design for the testing of lack of fit and for estimation in binary response models","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Mathematics; Statistics; Estimator; Binary data; Test statistic; Regression analysis; Econometrics; Statistical hypothesis testing; Binary number","score_opus":0.6072277121095938,"score_gpt":0.5422912207812377,"score_spread":0.0649364913283561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065015301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014258888,0.00013473968,0.9821345,0.000088854234,0.000013687283,0.0003547389,0.0030094814,0.000002618655,0.000002498557],"genre_scores_gemma":[0.39232928,0.0000020189486,0.6074759,0.000008908078,0.0000026165028,0.0000060181274,0.00016687816,0.0000028116444,0.000005602082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777234,0.00039790137,0.0008794941,0.00030399254,0.0005511451,0.00009514747],"domain_scores_gemma":[0.95850104,0.039783597,0.00056942785,0.0003922055,0.00072634633,0.000027397777],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006578871,0.00008794312,0.0003969733,0.00040938804,0.00006441473,0.000035400022,0.0005015395,0.00003069212,0.000007771087],"category_scores_gemma":[0.011335416,0.00006698576,0.00004914416,0.0014114318,0.00013789629,0.0002458413,0.00009251924,0.0000317131,9.5176695e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006132792,0.000072394854,0.00025791934,0.000012448438,0.000080152466,2.611897e-7,0.000120103956,0.97269166,0.00041268198,0.0035187644,0.00034076767,0.021879585],"study_design_scores_gemma":[0.00030750738,0.0002032147,0.019146515,0.000011888433,0.00023248239,4.3064546e-7,0.00007126873,0.8773245,0.00013291223,0.102512695,0.0000017706271,0.000054816173],"about_ca_topic_score_codex":0.000041390515,"about_ca_topic_score_gemma":0.0000048637357,"teacher_disagreement_score":0.37807038,"about_ca_system_score_codex":0.000016881646,"about_ca_system_score_gemma":0.000112634094,"threshold_uncertainty_score":0.9969925},"labels":[],"label_agreement":null},{"id":"W2066436413","doi":"10.1016/j.csda.2006.06.017","title":"An alternative estimation method for the accelerated failure time frailty model","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Efficiency Analysis Using DEA","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Estimation; Statistics; Mathematics; Econometrics; Computer science; Engineering","score_opus":0.18040306931004957,"score_gpt":0.47647808545699416,"score_spread":0.2960750161469446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066436413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074613077,0.00003728126,0.9842978,0.00078431476,0.000039926716,0.00022814094,0.013774212,0.00004384613,0.000048323265],"genre_scores_gemma":[0.2151062,0.0000010019763,0.7632889,0.00018928359,0.00007462488,0.000014469694,0.020991,0.000014132474,0.00032037336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950877,0.0004586112,0.0010697643,0.0010803549,0.0020252804,0.00027832272],"domain_scores_gemma":[0.98679817,0.008972051,0.00070429634,0.0015879753,0.0018486495,0.00008886365],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0044520167,0.00023690058,0.0005064517,0.0006541851,0.0007793913,0.001115922,0.0023568466,0.00006971896,0.00037201607],"category_scores_gemma":[0.0025070698,0.00016608283,0.00017550153,0.0034998606,0.00015722647,0.00076040963,0.00023782987,0.00014012543,0.00013090813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014110129,0.00009523665,0.00019703792,0.0000013058276,0.0005365093,0.0000013703919,0.00006879309,0.93551904,0.000032760152,0.020147387,0.029106922,0.014279508],"study_design_scores_gemma":[0.00015375606,0.000015087772,0.0032442808,0.0000012634619,0.0016638893,7.4516214e-7,0.00001779945,0.7387389,0.000007410994,0.2555404,0.00046314902,0.00015330208],"about_ca_topic_score_codex":0.0009584631,"about_ca_topic_score_gemma":0.0010964755,"teacher_disagreement_score":0.23539302,"about_ca_system_score_codex":0.00006346969,"about_ca_system_score_gemma":0.00020747841,"threshold_uncertainty_score":0.999921},"labels":[],"label_agreement":null},{"id":"W2068729564","doi":"10.1016/j.csda.2004.02.001","title":"On likelihood inference in binary mixed model with an application to COPD data","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Estimator; Statistics; Inference; Random effects model; Mathematics; Binary data; Monte Carlo method; Binary number; Mixed model; Statistical inference; Moment (physics); Computer science; Artificial intelligence; Medicine","score_opus":0.10092335098585019,"score_gpt":0.4170239513736352,"score_spread":0.316100600387785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068729564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037465047,0.000005109485,0.97741336,0.00020814888,0.000016111278,0.00029109322,0.01822773,0.000045878194,0.000046053436],"genre_scores_gemma":[0.27054906,0.0000037153052,0.71295017,0.00016049562,0.000016939852,0.000023438815,0.016274232,0.000018642899,0.0000033140593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972948,0.00014423276,0.0005672711,0.0010237503,0.00066466717,0.00030529095],"domain_scores_gemma":[0.99477684,0.002490512,0.00019533225,0.002038815,0.0002561568,0.00024231047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007039213,0.00025018596,0.00047142623,0.00040015051,0.00012288828,0.00012647526,0.0012651463,0.00006378744,0.00004773691],"category_scores_gemma":[0.0019507597,0.00022505475,0.000019940033,0.001459148,0.00008491597,0.0003266677,0.00048119875,0.00020207583,0.000041848492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068578214,0.00041201658,0.00048154444,0.0000272563,0.00015327807,0.000016470523,0.00008883354,0.3692425,0.000004228112,0.61185867,0.00054208015,0.017104572],"study_design_scores_gemma":[0.0002488206,0.00009421395,0.0050894152,0.000020368498,0.00027490282,5.5156437e-7,0.000011594977,0.50947815,9.554132e-7,0.48461363,0.000007792911,0.00015963046],"about_ca_topic_score_codex":0.00050473324,"about_ca_topic_score_gemma":0.0029379637,"teacher_disagreement_score":0.26680255,"about_ca_system_score_codex":0.00010539313,"about_ca_system_score_gemma":0.0003127565,"threshold_uncertainty_score":0.91774666},"labels":[],"label_agreement":null},{"id":"W2069557700","doi":"10.1016/j.csda.2004.05.022","title":"Exact tests of the stability of the Phillips curve: the Canadian case","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Bank of Canada; Université de Montréal; Université Laval","funders":"","keywords":"Mathematics; Nuisance parameter; Test statistic; Applied mathematics; Kalman filter; Inflation (cosmology); Stability (learning theory); Constant (computer programming); Monte Carlo method; Statistic; Lag; Econometrics; Statistics; Statistical hypothesis testing; Type I and type II errors; Computer science; Estimator","score_opus":0.12057488506500937,"score_gpt":0.27735232483732786,"score_spread":0.1567774397723185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069557700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8121042,0.00033790586,0.07064038,0.0030726676,0.00022841874,0.0003233439,0.11261331,0.0000055794253,0.00067419134],"genre_scores_gemma":[0.9959971,0.000013278891,0.0029845985,0.00024289271,0.000031064996,0.0000023034295,0.0007027972,0.0000074018417,0.00001861726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9986935,0.000058981685,0.0006907616,0.00028804972,0.000075281,0.00019340434],"domain_scores_gemma":[0.9977237,0.00036330937,0.0005722253,0.0012083815,0.000053521835,0.00007883624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008397597,0.00011513589,0.00032201165,0.0001288986,0.00036957528,0.000047806123,0.00081458583,0.00004244077,0.00037092384],"category_scores_gemma":[0.0005209263,0.000077045726,0.00014625974,0.0006853017,0.00030163862,0.00012366085,0.00018821309,0.00014012218,0.000022263386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004050064,0.000061009396,0.34446707,0.000020667476,0.0008316576,0.0000045810416,0.00047959515,0.54360557,3.2201672e-7,0.108828925,0.0014122773,0.00028426407],"study_design_scores_gemma":[0.00017103103,0.0000085766005,0.7244996,0.000003660864,0.00021359036,0.000013218075,0.00002396141,0.17595112,0.0000039470683,0.098092675,0.0009184529,0.00010017778],"about_ca_topic_score_codex":0.46464148,"about_ca_topic_score_gemma":0.5330505,"teacher_disagreement_score":0.38003254,"about_ca_system_score_codex":0.00017533827,"about_ca_system_score_gemma":0.00022907129,"threshold_uncertainty_score":0.5389235},"labels":[],"label_agreement":null},{"id":"W2070637054","doi":"10.1016/s0167-9473(02)00184-6","title":"Fitting semiparametric cure models","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Proportional hazards model; Semiparametric regression; Logistic regression; Computer science; Semiparametric model; Econometrics; Mathematics; Regression; Statistics; Nonparametric statistics","score_opus":0.25250469355321736,"score_gpt":0.4304173403249091,"score_spread":0.17791264677169172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070637054","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065218576,0.00009585709,0.99155056,0.000038944756,0.000067639485,0.000106570464,0.0056315935,0.000053224943,0.0018034017],"genre_scores_gemma":[0.10394027,0.000024985759,0.89368516,0.00010183213,0.000029567846,0.0000069506445,0.0020641806,0.000020247937,0.00012679695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99739635,0.00035842162,0.0006566697,0.00060482114,0.00066973706,0.00031401726],"domain_scores_gemma":[0.99082464,0.007507628,0.00027596837,0.00081727863,0.00040450308,0.00016999766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012248014,0.00021679755,0.00050322904,0.00040896705,0.00020911296,0.00014160325,0.00047647432,0.00007139986,0.0007987843],"category_scores_gemma":[0.00867083,0.00020728199,0.00008365031,0.0023127955,0.00009030864,0.00017505913,0.00016876025,0.00020938042,0.00004095802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003007212,0.00009290143,0.0014374311,0.000033684624,0.00063730235,0.000010907767,0.000047653662,0.042400848,6.1146574e-7,0.93680966,0.011636474,0.0068895468],"study_design_scores_gemma":[0.00009189232,0.000009349142,0.00089628476,0.0000049129544,0.0007812417,0.0000020468976,0.000011278926,0.4868997,0.0000010716376,0.5107625,0.00040667885,0.00013301312],"about_ca_topic_score_codex":0.00007967681,"about_ca_topic_score_gemma":0.000028240129,"teacher_disagreement_score":0.44449884,"about_ca_system_score_codex":0.000048905862,"about_ca_system_score_gemma":0.0001208813,"threshold_uncertainty_score":0.99967957},"labels":[],"label_agreement":null},{"id":"W2071909737","doi":"10.1016/s0167-9473(03)00029-x","title":"Robust estimation under progressive censoring","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Censoring (clinical trials); Statistics; Mathematics; Estimation; Econometrics; Computer science; Economics","score_opus":0.2216471929200212,"score_gpt":0.4167056230781298,"score_spread":0.19505843015810861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071909737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045027776,0.000030504183,0.98972714,0.00018607479,0.00004440763,0.00021986087,0.0085963495,0.000112397145,0.0006329865],"genre_scores_gemma":[0.2577082,0.000003619766,0.72426176,0.00008961894,0.000018090519,0.000031859538,0.017763956,0.000016245496,0.00010666331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978608,0.0001540803,0.00060417305,0.00054110395,0.0005817358,0.00025814428],"domain_scores_gemma":[0.99671584,0.0016380313,0.00030867878,0.00070995645,0.0004598338,0.00016763226],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041765766,0.00020214067,0.00032131904,0.00020975212,0.00035645431,0.00016314109,0.00032069779,0.00006104712,0.001591147],"category_scores_gemma":[0.0024122992,0.00020785903,0.0000679763,0.0012712635,0.00013047407,0.000218704,0.00008846655,0.00013809388,0.00016019105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024887695,0.00012769601,0.00024175544,0.000019115045,0.00036978448,0.000003540368,0.000018713965,0.19693746,7.5257094e-7,0.7929191,0.007979089,0.0013804862],"study_design_scores_gemma":[0.00016284945,0.000005698607,0.007897802,0.00000550181,0.00079536956,0.0000040566165,0.000020405994,0.56474537,0.0000030414717,0.4258475,0.0003659393,0.0001464864],"about_ca_topic_score_codex":0.000020999809,"about_ca_topic_score_gemma":0.000021866283,"teacher_disagreement_score":0.3678079,"about_ca_system_score_codex":0.00010035022,"about_ca_system_score_gemma":0.000121602665,"threshold_uncertainty_score":0.9993215},"labels":[],"label_agreement":null},{"id":"W2072196320","doi":"10.1016/j.csda.2007.09.022","title":"Identification-robust simulation-based inference in joint discrete/continuous models for energy markets","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Université Laval","funders":"","keywords":"Context (archaeology); Inference; Identification (biology); Instrumental variable; Econometrics; Monte Carlo method; Computer science; Logit; Curse of dimensionality; Mathematical optimization; Discrete choice; Statistical inference; Mathematics; Statistics; Machine learning; Artificial intelligence","score_opus":0.14873746570838683,"score_gpt":0.2951493901335995,"score_spread":0.14641192442521264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072196320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017521031,0.00010874062,0.972701,0.000042638305,0.0000685663,0.00015048137,0.009310596,0.000011212631,0.00008574026],"genre_scores_gemma":[0.8549729,0.000012355937,0.12944749,0.00008413062,0.00002957135,0.000014041551,0.015358591,0.000014924264,0.000066008026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979961,0.00002144948,0.0010991294,0.00058561517,0.0000807851,0.00021695445],"domain_scores_gemma":[0.99773175,0.001143705,0.00054086285,0.0004535032,0.00005948107,0.000070728915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012448265,0.00014309958,0.00036814593,0.0005268868,0.0001134712,0.000087646156,0.0002787292,0.00006395552,0.00025035546],"category_scores_gemma":[0.00037143778,0.00018860008,0.00008203556,0.0004170115,0.000056404286,0.00037355773,0.000076407174,0.00005487937,0.000030334617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013146387,0.0000667224,0.058284122,0.000008729701,0.0001504379,8.6294835e-7,0.00002786859,0.8603694,0.0000010478803,0.08030482,0.00007507088,0.00069776986],"study_design_scores_gemma":[0.00030886565,0.0000068246954,0.18156973,0.0000027466801,0.00008075424,5.3463708e-8,0.000010635428,0.71663254,0.0000014369846,0.10114543,0.00008880919,0.00015218377],"about_ca_topic_score_codex":0.0007334526,"about_ca_topic_score_gemma":0.0005557579,"teacher_disagreement_score":0.8432535,"about_ca_system_score_codex":0.00022149654,"about_ca_system_score_gemma":0.000035850975,"threshold_uncertainty_score":0.7690888},"labels":[],"label_agreement":null},{"id":"W2074211846","doi":"10.1016/j.csda.2009.03.006","title":"A note on interval estimation of using lower record data from the generalized exponential distribution","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Exponential distribution; Exponential family; Statistics; Applied mathematics; Gamma distribution; Interval estimation; Exponential function; Phase-type distribution; Interval (graph theory); Confidence interval; Combinatorics; Mathematical analysis","score_opus":0.1983595243107808,"score_gpt":0.4122361611757882,"score_spread":0.2138766368650074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074211846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012392295,0.000032111493,0.9494254,0.00023839052,0.00021326148,0.0000918515,0.03758555,0.000015962794,0.000005196858],"genre_scores_gemma":[0.55179167,0.000004214151,0.40406898,0.00006960103,0.00007547401,5.6194665e-7,0.043976676,0.000004095603,0.000008711691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969541,0.00025277815,0.00082788663,0.00063431944,0.0011884695,0.0001424587],"domain_scores_gemma":[0.99432427,0.0030797557,0.00042184844,0.00178801,0.00032435876,0.00006176687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001559846,0.00014638073,0.00036120048,0.00013487187,0.0001672484,0.00021001478,0.0017741056,0.00004831466,0.0002409667],"category_scores_gemma":[0.004759539,0.0001021078,0.00007344518,0.0010679989,0.000092147224,0.00032147265,0.00037111167,0.00011137879,0.000032992742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000701761,0.000081882295,0.0002448314,0.0000011210295,0.00019448037,0.000003865093,0.000032119322,0.9462399,0.0000133165195,0.0046373904,0.018140215,0.030340722],"study_design_scores_gemma":[0.00019110853,0.000028751037,0.024029087,0.000012022224,0.00067306176,5.9924264e-7,0.0000058067753,0.9150421,0.0000020328193,0.0594725,0.0004377943,0.00010514749],"about_ca_topic_score_codex":0.000488509,"about_ca_topic_score_gemma":0.00007584718,"teacher_disagreement_score":0.5453564,"about_ca_system_score_codex":0.00005599027,"about_ca_system_score_gemma":0.00010464436,"threshold_uncertainty_score":0.56979567},"labels":[],"label_agreement":null},{"id":"W2077144637","doi":"10.1016/j.csda.2004.10.014","title":"Modified censored moment estimation for the two-parameter Birnbaum–Saunders distribution","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Censoring (clinical trials); Estimator; Mathematics; Statistics; Moment (physics); Monte Carlo method; Maximum likelihood; Asymptotic distribution; Econometrics","score_opus":0.12732889635048777,"score_gpt":0.4131406792489557,"score_spread":0.2858117828984679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077144637","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042805268,0.000018114235,0.93686086,0.001966566,0.00006459386,0.0006603511,0.059881024,0.000094888484,0.000025524569],"genre_scores_gemma":[0.4169243,0.000006360423,0.50324774,0.00013002507,0.00003319655,0.00014501113,0.0794675,0.00001427742,0.000031633004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773407,0.000070326285,0.00073540094,0.0005492028,0.0006123335,0.00029869087],"domain_scores_gemma":[0.9941356,0.00400653,0.0003517225,0.00084216177,0.0005264742,0.00013748615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005212727,0.00023512158,0.00033644968,0.00011844398,0.00065513904,0.00021696724,0.0005107246,0.000058965605,0.0001307143],"category_scores_gemma":[0.0019871136,0.00019578669,0.00013418206,0.001002362,0.00021260421,0.00018833486,0.00012425892,0.0001290915,0.0000487956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014227142,0.00011664541,0.000016157655,0.000016657146,0.00043757647,4.719067e-7,0.000025656092,0.4065301,0.000001176153,0.5831706,0.0062150746,0.0034556806],"study_design_scores_gemma":[0.0005766687,0.000012019678,0.003354546,0.0000043919717,0.0013104029,0.0000011754795,0.000015880683,0.5444225,0.0000037770762,0.44975027,0.0004212338,0.00012715353],"about_ca_topic_score_codex":0.00016628379,"about_ca_topic_score_gemma":0.00010523968,"teacher_disagreement_score":0.43361318,"about_ca_system_score_codex":0.0002669689,"about_ca_system_score_gemma":0.00013643088,"threshold_uncertainty_score":0.7983949},"labels":[],"label_agreement":null},{"id":"W2081290294","doi":"10.1016/j.csda.2008.01.014","title":"Approximation of powers of some tests in one-way MANOVA type multivariate generalized linear model","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pacific Institute for the Mathematical Sciences","keywords":"Mathematics; Multivariate analysis of variance; Multivariate statistics; Generalized linear model; Deviance (statistics); Statistics; Applied mathematics; Sample size determination; Statistic; Test statistic; Linear model; Type I and type II errors; Statistical hypothesis testing","score_opus":0.3767989769850297,"score_gpt":0.48334965061897744,"score_spread":0.10655067363394777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081290294","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064064935,0.000078722805,0.93293995,0.000025408106,0.000036739828,0.0001330075,0.0026139999,0.000008689758,0.00009856807],"genre_scores_gemma":[0.37272543,0.000013016308,0.62527645,0.000022266204,0.000008960885,0.0000017964661,0.0018650012,0.0000075053567,0.000079565994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960795,0.0003929508,0.0012935224,0.00055505766,0.0015164288,0.00016252257],"domain_scores_gemma":[0.9959353,0.0017293502,0.0006787029,0.00078174577,0.00079965923,0.00007523163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018862577,0.00015118402,0.0006426529,0.0008873873,0.00006506065,0.000027273903,0.00083052367,0.00006188448,0.0002611996],"category_scores_gemma":[0.0026879578,0.00014186263,0.00008445494,0.0026788805,0.00020350715,0.00044391133,0.00031508127,0.000094940675,0.000036760834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009204673,0.0002610563,0.003949263,0.000008482892,0.00025395674,0.000005260176,0.00033204796,0.97566426,0.0023697137,0.014989588,0.000560299,0.0015140091],"study_design_scores_gemma":[0.00044836616,0.000036698406,0.037527315,0.000005517559,0.00014668301,9.308958e-7,0.000022464668,0.9104659,0.0003324959,0.050878897,0.000012944116,0.00012177184],"about_ca_topic_score_codex":0.00050561485,"about_ca_topic_score_gemma":0.000034148627,"teacher_disagreement_score":0.3086605,"about_ca_system_score_codex":0.00005071765,"about_ca_system_score_gemma":0.00017828928,"threshold_uncertainty_score":0.578499},"labels":[],"label_agreement":null},{"id":"W2081807443","doi":"10.1016/j.csda.2010.04.013","title":"Optimal allocation of change points in simple step-stress experiments under Type-II censoring","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Censoring (clinical trials); Mathematics; Simple (philosophy); Statistics; Mathematical optimization; Applied mathematics","score_opus":0.22573843301258328,"score_gpt":0.44379391499658666,"score_spread":0.21805548198400337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081807443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051980313,0.000008659912,0.9344248,0.00014465718,0.00005049874,0.00019793524,0.013107424,0.000027476659,0.000058207403],"genre_scores_gemma":[0.59485596,0.0000037874631,0.38471818,0.00003692738,0.000025303512,0.000021971924,0.02030507,0.000009942674,0.00002286521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998331,0.000060551127,0.0006114706,0.00037350465,0.00043568184,0.00018776387],"domain_scores_gemma":[0.9979191,0.00072204013,0.00027586066,0.0005681204,0.0004143153,0.000100589794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028212764,0.00014931933,0.0003035137,0.0002440955,0.00013722041,0.000049088478,0.0003503342,0.000065579385,0.00075877534],"category_scores_gemma":[0.00072801014,0.00016145127,0.000040057548,0.0009939312,0.00010341931,0.00024379788,0.0002092996,0.00015455796,0.000021198875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016170325,0.00053585623,0.0036289603,0.00004458026,0.00028611315,0.0000021450749,0.00018443842,0.011971004,0.00012637752,0.9793187,0.0020859707,0.0017997232],"study_design_scores_gemma":[0.00037820602,0.000019434026,0.12150144,0.000011710873,0.0003779121,9.836269e-7,0.000079368445,0.813068,0.00007813556,0.06403388,0.00026320998,0.0001877561],"about_ca_topic_score_codex":0.00026101418,"about_ca_topic_score_gemma":0.00035382455,"teacher_disagreement_score":0.91528475,"about_ca_system_score_codex":0.000045163648,"about_ca_system_score_gemma":0.000061798266,"threshold_uncertainty_score":0.8308058},"labels":[],"label_agreement":null},{"id":"W2082194214","doi":"10.1016/j.csda.2012.02.021","title":"Computation of optimal plotting points based on Pitman closeness with an application to goodness-of-fit for location-scale families","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; McMaster University","funders":"","keywords":"Goodness of fit; Quantile; Nonparametric statistics; Statistics; Mathematics; Closeness; Population; Percentile; Scale (ratio); Order statistic; Normality; Econometrics; Cartography; Geography","score_opus":0.11036005916284936,"score_gpt":0.4132182649145446,"score_spread":0.30285820575169525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082194214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01614691,0.000005261323,0.96824664,0.00013227358,0.000021100637,0.00064606685,0.0147216255,0.000048796905,0.000031326017],"genre_scores_gemma":[0.51278085,3.8159124e-7,0.47142643,0.000048841965,0.00002218177,0.00008181739,0.015621652,0.000015327665,0.0000025464535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978256,0.00010195458,0.0007907285,0.00043623775,0.0006100224,0.00023542343],"domain_scores_gemma":[0.99527997,0.0020512093,0.00057756767,0.00063405145,0.0012598945,0.00019730761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061277795,0.0002078348,0.00044694793,0.00035912375,0.0001916215,0.000038115762,0.00034755727,0.00005752056,0.000030197438],"category_scores_gemma":[0.0006437739,0.0002044598,0.000055768385,0.0014743892,0.00012798239,0.000233192,0.00005932263,0.0000683471,0.000011171152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011489463,0.0008859507,0.0037572016,0.00021053241,0.00022721452,9.238586e-8,0.000220762,0.60856044,0.000024526038,0.3797185,0.0004545421,0.0058253356],"study_design_scores_gemma":[0.00046547555,0.00013603573,0.057105005,0.000037895727,0.000931767,4.749395e-7,0.00015087887,0.92222804,0.00009367168,0.018594358,0.00004837165,0.00020803371],"about_ca_topic_score_codex":0.000075712545,"about_ca_topic_score_gemma":0.00006213677,"teacher_disagreement_score":0.4968202,"about_ca_system_score_codex":0.00006689736,"about_ca_system_score_gemma":0.000121906676,"threshold_uncertainty_score":0.8337628},"labels":[],"label_agreement":null},{"id":"W2084128712","doi":"10.1016/j.csda.2010.07.016","title":"Vine copulas with asymmetric tail dependence and applications to financial return data","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":211,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Vine copula; Copula (linguistics); Tail dependence; Bivariate analysis; Econometrics; Quantile; Multivariate statistics; Mathematics; Joint probability distribution; Tail risk; Statistics; Economics","score_opus":0.05593794019861853,"score_gpt":0.2905389719159295,"score_spread":0.23460103171731095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084128712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010654649,0.00023175667,0.953633,0.00021065866,0.00006106615,0.00020987663,0.0347774,0.000022855222,0.00019874715],"genre_scores_gemma":[0.5834884,0.00005675109,0.40164357,0.00015737592,0.0001210337,0.000016409653,0.014451674,0.000014110666,0.000050653747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801725,0.000013415172,0.00059110817,0.0010043448,0.00014255707,0.00023133848],"domain_scores_gemma":[0.9976547,0.00028084283,0.00027207416,0.0014468571,0.0001758469,0.00016969022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071461016,0.00016903896,0.00041993102,0.0005414653,0.00028062542,0.00017790476,0.00092789694,0.00007563182,0.00009804017],"category_scores_gemma":[0.00088404975,0.00018802115,0.0000258558,0.0018677239,0.00008626875,0.00038245082,0.0006357487,0.00025400383,0.000095905685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005395053,0.00020254034,0.3893292,0.00004694463,0.00046876256,0.000010110394,0.00011558235,0.029782899,0.0000029636506,0.53023446,0.006849352,0.04290325],"study_design_scores_gemma":[0.00017596548,0.000025115178,0.1895976,0.000002831035,0.000185089,0.0000023588618,0.0000042025167,0.7439164,3.270136e-7,0.045949318,0.019916596,0.00022422466],"about_ca_topic_score_codex":0.0016397901,"about_ca_topic_score_gemma":0.0056745084,"teacher_disagreement_score":0.7141335,"about_ca_system_score_codex":0.000026854726,"about_ca_system_score_gemma":0.00010243537,"threshold_uncertainty_score":0.766728},"labels":[],"label_agreement":null},{"id":"W2084235223","doi":"10.1016/j.csda.2012.01.011","title":"Bootstrap testing multiple changes in persistence for a heavy-tailed sequence","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Test statistic; Null hypothesis; Mathematics; Null (SQL); Null distribution; Statistics; Econometrics; Alternative hypothesis; Statistical hypothesis testing; Sequence (biology); Sequential analysis; Score test; Statistic; Computer science; Data mining","score_opus":0.3345250071365134,"score_gpt":0.32346507158546384,"score_spread":0.01105993555104956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084235223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013308698,0.0008880961,0.96298236,0.00022378677,0.0001009906,0.0002342259,0.022015918,0.000026417156,0.00021952255],"genre_scores_gemma":[0.81776446,0.00001662679,0.17586419,0.00007833482,0.00010506921,0.000036081805,0.00600148,0.000015354264,0.00011840943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981659,0.00002960757,0.00071825896,0.0005674802,0.00009817602,0.00042056444],"domain_scores_gemma":[0.99788976,0.0008429982,0.00044955712,0.00054479495,0.00014432667,0.00012854654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861427,0.00018024477,0.0006115527,0.0005560319,0.00019565385,0.000119887096,0.00042560138,0.00005041763,0.00032226267],"category_scores_gemma":[0.0008602901,0.00021552661,0.00011161359,0.0015337231,0.00006309401,0.00033246103,0.00016651695,0.00008648395,0.00006829613],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019845336,0.0001396991,0.8755537,0.00007513303,0.000966997,0.0000030539109,0.00032425893,0.05374065,0.000004710755,0.06626226,0.0007725721,0.0021370763],"study_design_scores_gemma":[0.00026470615,0.000023982142,0.14907773,0.000008861685,0.00022247547,0.0000017191898,0.000087752305,0.8377279,6.000636e-7,0.007622289,0.004719941,0.00024205876],"about_ca_topic_score_codex":0.002345669,"about_ca_topic_score_gemma":0.003644802,"teacher_disagreement_score":0.80445576,"about_ca_system_score_codex":0.000119270655,"about_ca_system_score_gemma":0.00003133853,"threshold_uncertainty_score":0.87889206},"labels":[],"label_agreement":null},{"id":"W2085557796","doi":"10.1016/j.csda.2006.05.019","title":"Generating good pseudo-random numbers","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Chaos-based Image/Signal Encryption","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université de Montréal; Drexel University","keywords":"Random number generation; Generator (circuit theory); Computer science; Random seed; Convolution random number generator; Pseudorandom number generator; Mathematics; Algorithm; Random variate; Random variable; Statistics; Power (physics)","score_opus":0.01848984362808755,"score_gpt":0.2785627869385038,"score_spread":0.26007294331041625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085557796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016283714,0.00007217716,0.99547774,0.0002542278,0.00012956842,0.00010751149,0.0018758934,0.00014514902,0.00030937334],"genre_scores_gemma":[0.19341375,0.0000052697637,0.7930163,0.00024673942,0.00016467382,0.000006922737,0.013005579,0.000013026071,0.00012771027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971818,0.00017654768,0.00061827706,0.0008500362,0.00085205596,0.00032131808],"domain_scores_gemma":[0.9974421,0.00076123903,0.00030266985,0.0010350615,0.00034614638,0.000112763715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059864204,0.00022985252,0.00035061594,0.00036058025,0.00033557537,0.0005731048,0.0012934053,0.000049351886,0.00013159189],"category_scores_gemma":[0.00015235781,0.00024584075,0.00010842915,0.0018175457,0.000078588906,0.00081589026,0.0005113959,0.00015117617,0.00014180302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006271962,0.00009502457,0.0024247677,0.00001040454,0.00036307628,0.00003944465,0.0000359837,0.8787122,0.00011248943,0.0920469,0.017204544,0.008948941],"study_design_scores_gemma":[0.00052974344,0.000015557065,0.008272133,0.0000046574023,0.00041489603,0.000008080013,0.0000032068015,0.9594922,0.000011747486,0.03015315,0.0008263808,0.00026821555],"about_ca_topic_score_codex":0.0018244346,"about_ca_topic_score_gemma":0.0005975039,"teacher_disagreement_score":0.20246139,"about_ca_system_score_codex":0.00010641817,"about_ca_system_score_gemma":0.00017069805,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W2086405403","doi":"10.1016/j.csda.2009.10.008","title":"Test of fit for a Laplace distribution against heavier tailed alternatives","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Laplace distribution; Kurtosis; Goodness of fit; Mathematics; Laplace transform; Estimator; Applied mathematics; Skewness; Distribution (mathematics); Statistics; Test statistic; Statistical hypothesis testing; Mathematical analysis","score_opus":0.12586457587613573,"score_gpt":0.4310709547122683,"score_spread":0.30520637883613255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086405403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010344912,0.000017954057,0.84977734,0.00050946494,0.000016763894,0.00028722268,0.14822865,0.000041335636,0.000086813445],"genre_scores_gemma":[0.5049877,0.000013519618,0.40041184,0.000102392405,0.000030868767,0.000026602922,0.09432955,0.000008093603,0.000089428344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982016,0.000053874304,0.0007126215,0.00041230576,0.00042137157,0.0001982113],"domain_scores_gemma":[0.9946987,0.0035122924,0.00041816974,0.00052547554,0.0007285916,0.000116757954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027640653,0.00017383869,0.00041047373,0.00012069797,0.00018980035,0.000060663337,0.00038149697,0.000050781466,0.00016025797],"category_scores_gemma":[0.0039083315,0.00017518524,0.000105116145,0.00083272165,0.00011310488,0.0001392202,0.0000630264,0.00008065118,0.000016372891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024819323,0.0005805146,0.000688388,0.00004703124,0.00040403832,0.0000012515019,0.000036196026,0.009508461,0.00002862316,0.9359948,0.042501125,0.010184756],"study_design_scores_gemma":[0.00039403082,0.000044103763,0.037597038,0.0000118081825,0.00078670005,5.478858e-7,0.000011707743,0.6543347,0.000018662831,0.305416,0.0012379941,0.00014670497],"about_ca_topic_score_codex":0.000012438508,"about_ca_topic_score_gemma":0.000019677766,"teacher_disagreement_score":0.64482623,"about_ca_system_score_codex":0.000071264774,"about_ca_system_score_gemma":0.00008544815,"threshold_uncertainty_score":0.7143847},"labels":[],"label_agreement":null},{"id":"W2087855743","doi":"10.1016/j.csda.2010.06.026","title":"Localized level crossing random walk test robust to the presence of structural breaks","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mathematics; Nonparametric statistics; Null hypothesis; Random walk; Statistical hypothesis testing; Statistics; Nominal level; Series (stratigraphy); Null (SQL); Econometrics; Algorithm; Computer science; Data mining","score_opus":0.11766825902184155,"score_gpt":0.2943412575245766,"score_spread":0.17667299850273507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087855743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08133244,0.00008945326,0.8670986,0.0005303274,0.00018781653,0.00013742477,0.050452508,0.000009798328,0.0001615968],"genre_scores_gemma":[0.8568301,0.0000058914056,0.13917208,0.0002142665,0.000108559456,0.0000038092187,0.0034948508,0.000011269534,0.00015914458],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983682,0.00002420044,0.00080987666,0.00046358624,0.00008317224,0.00025096934],"domain_scores_gemma":[0.997474,0.0010800118,0.00044039293,0.0008239602,0.00006076453,0.0001208328],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074426236,0.0001567012,0.0005047626,0.00025830348,0.00032375014,0.00027584194,0.0007932229,0.000053776264,0.000970914],"category_scores_gemma":[0.0012359276,0.00014254615,0.0000990751,0.00052416057,0.00020918953,0.0002588844,0.00024412881,0.00018098501,0.0001401213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036998314,0.0000325898,0.08395506,0.000013771228,0.0006144757,0.0000017635801,0.00033805578,0.8816198,0.000005107157,0.022803256,0.0082368925,0.002342234],"study_design_scores_gemma":[0.00038693807,0.000011252488,0.24315673,0.000002055333,0.00011753146,0.0000026159335,0.0000069988523,0.7365414,0.0000021500455,0.016604802,0.003034617,0.00013291177],"about_ca_topic_score_codex":0.0071505494,"about_ca_topic_score_gemma":0.0023548738,"teacher_disagreement_score":0.7754977,"about_ca_system_score_codex":0.000024992762,"about_ca_system_score_gemma":0.000047280766,"threshold_uncertainty_score":0.99994236},"labels":[],"label_agreement":null},{"id":"W2090001193","doi":"10.1016/j.csda.2010.01.003","title":"Bayesian inference and prediction of the inverse Weibull distribution for Type-II censored data","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":236,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Markov chain Monte Carlo; Statistics; Mathematics; Gibbs sampling; Estimator; Bayesian inference; Bayes' theorem; Weibull distribution; Bayesian probability; Inference; Computer science; Artificial intelligence","score_opus":0.1298647633813924,"score_gpt":0.40499858438414155,"score_spread":0.27513382100274913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090001193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022976708,0.0000031611899,0.77222884,0.00029052846,0.0000653766,0.00021592078,0.22486009,0.000021281996,0.000017155888],"genre_scores_gemma":[0.5276334,0.0000056725935,0.34477693,0.000029660796,0.000029569055,0.000011213117,0.1274746,0.0000067180385,0.00003220005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865556,0.0000503662,0.00046981778,0.00038999296,0.00030739125,0.00012689045],"domain_scores_gemma":[0.9964354,0.001538955,0.00029437893,0.0010982136,0.0005478105,0.000085251966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038680848,0.0001184217,0.00021735994,0.00005667224,0.00036063814,0.000048839953,0.00057600334,0.00006301171,0.00017936018],"category_scores_gemma":[0.0052961325,0.00009945351,0.000031986852,0.00066791696,0.000244979,0.0001584977,0.00047801333,0.00013302613,0.0000030435383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015113128,0.00015262427,0.0034547278,0.000056794033,0.0003087154,1.6612961e-7,0.000037303562,0.0012359238,0.000054918037,0.9306857,0.06179351,0.0022045134],"study_design_scores_gemma":[0.00019652593,0.0000125280685,0.05738813,0.0000051765423,0.0009428111,9.54579e-7,0.000008619926,0.7432249,0.000005840648,0.1955059,0.0026388215,0.00006979422],"about_ca_topic_score_codex":0.00005858416,"about_ca_topic_score_gemma":0.0004303123,"teacher_disagreement_score":0.74198896,"about_ca_system_score_codex":0.000019202424,"about_ca_system_score_gemma":0.00011517536,"threshold_uncertainty_score":0.63403475},"labels":[],"label_agreement":null},{"id":"W2091474414","doi":"10.1016/j.csda.2006.09.044","title":"Improving the estimation of Kendall's tau when censoring affects only one of the variables","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Censoring (clinical trials); Mathematics; Statistics; Estimator; Econometrics; Nonparametric statistics; Bivariate analysis; Covariate; Copula (linguistics); Context (archaeology); Inference; Computer science; Artificial intelligence","score_opus":0.05311670140950168,"score_gpt":0.3287748610317663,"score_spread":0.2756581596222646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091474414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036638088,0.000020205698,0.9815067,0.0002892895,0.00003018632,0.0002441138,0.01406086,0.000024993606,0.00015982379],"genre_scores_gemma":[0.5760254,0.0000013461648,0.4193972,0.000019656787,0.000020587033,0.000008566447,0.0044707255,0.000008216889,0.000048255304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981002,0.00014861376,0.0006733675,0.00027871836,0.0006445976,0.00015448141],"domain_scores_gemma":[0.9950115,0.003043623,0.00072422775,0.00078784814,0.00039482937,0.00003798518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005279976,0.00013903562,0.00031645808,0.0001025315,0.00026249318,0.00005535754,0.000585544,0.00004366598,0.00022856455],"category_scores_gemma":[0.0017610021,0.00010175349,0.00008651429,0.000890784,0.00023478252,0.00011179862,0.00023077175,0.00011185742,0.000005450229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004246936,0.00015807369,0.00077315635,0.00008905208,0.00026325465,2.158655e-7,0.000035815538,0.12905492,0.00005433319,0.8611517,0.0047831093,0.0036321606],"study_design_scores_gemma":[0.00012921901,0.0000057252273,0.061705638,0.000016014965,0.001082781,8.3367365e-7,0.000011411081,0.61722785,0.000062171894,0.31963894,0.00004825135,0.0000711794],"about_ca_topic_score_codex":0.0007831992,"about_ca_topic_score_gemma":0.00020907138,"teacher_disagreement_score":0.57236165,"about_ca_system_score_codex":0.00005124271,"about_ca_system_score_gemma":0.00014830414,"threshold_uncertainty_score":0.4149387},"labels":[],"label_agreement":null},{"id":"W2094716207","doi":"10.1016/j.csda.2008.12.011","title":"Variance estimation of survey estimates calibrated on estimated control totals—An application to the extended regression estimator and the regression composite estimator","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Water Quality and Resources Studies","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"Universidad de Granada; University of Southampton","keywords":"Statistics; Estimator; Mathematics; Calibration; Weighting; Sampling (signal processing); Variance (accounting); Regression analysis; Regression; Bias of an estimator; Minimum-variance unbiased estimator; Computer science","score_opus":0.04273553965872416,"score_gpt":0.3184326612288662,"score_spread":0.27569712157014203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094716207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04904961,0.00008137084,0.94578946,0.0019255223,0.000029917855,0.00054509327,0.00250292,0.000049667164,0.000026456522],"genre_scores_gemma":[0.85652614,0.000013062336,0.13783158,0.0003605871,0.000014665589,0.000022246953,0.005203485,0.000011744312,0.000016499549],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970866,0.000630775,0.00064945064,0.0006578997,0.0007351809,0.00024012505],"domain_scores_gemma":[0.9965628,0.0018421608,0.00047042477,0.00087758346,0.00010353687,0.00014351205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014695887,0.00028649208,0.0005339761,0.000100935285,0.00083178974,0.00015930175,0.000679767,0.00006555395,0.00004520199],"category_scores_gemma":[0.0007190575,0.0001578202,0.000049235914,0.0010016762,0.00049817975,0.00026056272,0.00027589675,0.00015101276,0.000036913425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047731627,0.00017153083,0.010292669,0.000011532419,0.00022941917,0.0000025005888,0.00032048507,0.96888137,0.00008918098,0.002734488,0.0021760266,0.014613473],"study_design_scores_gemma":[0.00046329515,0.000057173915,0.41682172,0.000025770096,0.0003562341,0.00000221971,0.000009868598,0.5769167,0.000021285605,0.005188903,0.00002245053,0.00011439541],"about_ca_topic_score_codex":0.002243806,"about_ca_topic_score_gemma":0.00032033952,"teacher_disagreement_score":0.8079578,"about_ca_system_score_codex":0.00005348307,"about_ca_system_score_gemma":0.000020607375,"threshold_uncertainty_score":0.64357215},"labels":[],"label_agreement":null},{"id":"W2094738721","doi":"10.1016/j.csda.2009.07.018","title":"Recurrence relations for bivariate and extended skew- distributions and an application to order statistics from bivariate","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bivariate analysis; Mathematics; Skew; Order statistic; Recurrence relation; Joint probability distribution; Statistics; Cumulative distribution function; Distribution (mathematics); Applied mathematics; Probability density function; Combinatorics; Mathematical analysis; Computer science","score_opus":0.06872430094740863,"score_gpt":0.41496160760695067,"score_spread":0.34623730665954205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094738721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006339137,0.000022683063,0.8007413,0.0009907795,0.000024257512,0.0005565184,0.1969327,0.000075947595,0.000021877964],"genre_scores_gemma":[0.14399223,0.000016390039,0.7407431,0.00018100294,0.00004808517,0.00009101417,0.11488464,0.000013987988,0.000029573617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99758756,0.00011351253,0.0007586589,0.0008852164,0.0003730713,0.0002819781],"domain_scores_gemma":[0.99508303,0.0026101759,0.00030873125,0.0007663475,0.0008440211,0.00038766733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040026646,0.00026650424,0.00042068047,0.00023024662,0.0006454571,0.00026559198,0.00033102743,0.00009209583,0.00014258853],"category_scores_gemma":[0.0026275644,0.00028862403,0.000033166532,0.0012069619,0.00013253957,0.00028865744,0.00012874158,0.00014001677,0.000028685605],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023348897,0.0002604519,0.00029181052,0.00001295213,0.00022469202,7.508387e-7,0.000097480784,0.0014800144,0.000016979338,0.965424,0.0074871792,0.024680363],"study_design_scores_gemma":[0.00022386358,0.000040195428,0.0995073,0.0000052267646,0.00080914685,7.5633903e-7,0.000009049335,0.42760354,9.4897155e-7,0.470973,0.00065688515,0.00017005479],"about_ca_topic_score_codex":0.0002193032,"about_ca_topic_score_gemma":0.0002538052,"teacher_disagreement_score":0.49445096,"about_ca_system_score_codex":0.00007150262,"about_ca_system_score_gemma":0.000118485405,"threshold_uncertainty_score":0.9999566},"labels":[],"label_agreement":null},{"id":"W2097795807","doi":"10.1016/j.csda.2009.09.020","title":"Robust smoothing of gridded data in one and higher dimensions with missing values","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":1019,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Smoothing; Missing data; MATLAB; Algorithm; Computer science; Data mining; Mathematics; Statistics; Machine learning","score_opus":0.1849002830677711,"score_gpt":0.3584893633092068,"score_spread":0.17358908024143568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097795807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004315688,0.00012149041,0.9891041,0.00041647075,0.000015591133,0.00008595587,0.0058565643,0.00002163261,0.00006251526],"genre_scores_gemma":[0.1316741,0.000026700567,0.86145896,0.00009497757,0.000026308942,8.205562e-7,0.006685012,0.0000102210615,0.000022904804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811673,0.0000994954,0.00052826246,0.0005357652,0.0005257186,0.00019402217],"domain_scores_gemma":[0.9963893,0.0023784307,0.00021200956,0.0007555358,0.0001512764,0.00011340625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003959475,0.00016091077,0.00051953946,0.00020214688,0.00010338136,0.00006084369,0.0004218119,0.00003955014,0.000111907815],"category_scores_gemma":[0.00069097796,0.00013512571,0.000019102348,0.000873994,0.00014473575,0.00021630905,0.00029619294,0.00014223327,0.0000020184666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034813586,0.0034090092,0.02347174,0.00046469978,0.0052322764,0.0002986457,0.00093238853,0.049796768,0.000090414665,0.67074203,0.015846454,0.22936746],"study_design_scores_gemma":[0.00029691702,0.000048182836,0.115219645,0.000042060296,0.0010877567,0.0000017832756,0.000013672328,0.55699974,0.0000014530004,0.3261162,0.000030469384,0.0001421293],"about_ca_topic_score_codex":0.00031669578,"about_ca_topic_score_gemma":0.0000953361,"teacher_disagreement_score":0.5072029,"about_ca_system_score_codex":0.000020746584,"about_ca_system_score_gemma":0.00005018248,"threshold_uncertainty_score":0.55102664},"labels":[],"label_agreement":null},{"id":"W2100662412","doi":"10.1016/s0167-9473(02)00289-x","title":"Visualizing categorical data in ViSta","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Computer science; Interactivity; Correspondence analysis; Visualization; Bar chart; Data visualization; Statistical analysis; Data mining; R package; Mathematics; Statistics; Machine learning; Programming language; World Wide Web","score_opus":0.16947718887655253,"score_gpt":0.3900978698834989,"score_spread":0.2206206810069464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100662412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01689137,0.00014392502,0.9715335,0.00019306618,0.000054097174,0.00008687,0.0107398145,0.00002856442,0.00032883955],"genre_scores_gemma":[0.6998424,0.000036294656,0.2503502,0.00019684833,0.000059960363,0.000002809199,0.049444225,0.0000017495369,0.00006550562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698424,0.00065534114,0.00060096005,0.0009166234,0.00052758516,0.00031526704],"domain_scores_gemma":[0.9961701,0.0028911536,0.0001530821,0.00049407786,0.00013225581,0.00015934373],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014450629,0.00018338607,0.00045804578,0.00008660822,0.00020272098,0.00017985764,0.0009761099,0.000065243476,0.00146088],"category_scores_gemma":[0.0019727773,0.000091583664,0.00005958611,0.0023591418,0.00008328802,0.00022642968,0.000357585,0.00016536559,0.00004747529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005732569,0.0010092387,0.17788732,0.000029212266,0.0020604865,0.00028579787,0.00008813609,0.027828546,0.0004453417,0.6133301,0.01336792,0.16361058],"study_design_scores_gemma":[0.00012535857,0.000029494506,0.2682889,0.0000028973566,0.00074242265,0.0000039551633,0.0000626672,0.6698657,0.0000024274514,0.046519235,0.014073539,0.00028333152],"about_ca_topic_score_codex":0.0012762245,"about_ca_topic_score_gemma":0.0035152931,"teacher_disagreement_score":0.72118324,"about_ca_system_score_codex":0.00003709923,"about_ca_system_score_gemma":0.000029235824,"threshold_uncertainty_score":0.99945194},"labels":[],"label_agreement":null},{"id":"W2108832093","doi":"10.1016/j.csda.2004.11.011","title":"Linear grouping using orthogonal regression","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University; York University","funders":"Mitacs","keywords":"Hyperplane; Principal component analysis; Linear regression; Cluster analysis; Resampling; Mathematics; Computer science; Linear model; Data set; Set (abstract data type); Algorithm; Artificial intelligence; Statistics; Combinatorics","score_opus":0.3269742727101041,"score_gpt":0.5135506723646595,"score_spread":0.18657639965455536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108832093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038000178,0.00004818406,0.9899925,0.0000659765,0.00007413161,0.000113361166,0.0058005056,0.000058578484,0.000046759174],"genre_scores_gemma":[0.056855265,0.000014598428,0.9379382,0.000094462164,0.000106075335,0.0000031848488,0.004933769,0.000029220497,0.000025184114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976621,0.00013061277,0.0006273554,0.0006323056,0.00064601266,0.0003015962],"domain_scores_gemma":[0.9970208,0.0015325306,0.00030274625,0.00066601357,0.00030444027,0.00017346055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005801165,0.00023396485,0.0004985578,0.00024221827,0.00031505374,0.00006050893,0.00038922767,0.00006892896,0.0001411833],"category_scores_gemma":[0.0015462488,0.00021060156,0.00009391788,0.0008199767,0.000117142146,0.00025711837,0.00033643143,0.00019973764,0.000013849055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017526883,0.000110423316,0.00027201336,0.000039288025,0.0005284999,0.000045637116,0.000058665708,0.39444354,0.000020876409,0.59847766,0.00023028137,0.0057556056],"study_design_scores_gemma":[0.00021490458,0.000011180452,0.000591524,0.000022491644,0.0008047719,0.0000049509727,0.000008360028,0.482053,0.0000030367191,0.5160679,0.00007361707,0.00014420967],"about_ca_topic_score_codex":0.00010417991,"about_ca_topic_score_gemma":0.00008356333,"teacher_disagreement_score":0.08760949,"about_ca_system_score_codex":0.000108519125,"about_ca_system_score_gemma":0.00014876107,"threshold_uncertainty_score":0.8588082},"labels":[],"label_agreement":null},{"id":"W2127767112","doi":"10.1016/j.csda.2004.06.004","title":"An extended redundancy analysis and its applications to two practical examples","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Redundancy (engineering); Computer science; Algorithm; Extension (predicate logic); Mathematics; Data mining; Mathematical optimization","score_opus":0.06267678262749984,"score_gpt":0.41874281960770926,"score_spread":0.35606603698020944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127767112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015724145,0.00022055596,0.97548753,0.0003063355,0.000006713995,0.00008395122,0.007885846,0.00007707996,0.00020786344],"genre_scores_gemma":[0.5904038,0.000053205997,0.389201,0.00012677562,0.00007312036,0.000029893554,0.020025682,0.000014870966,0.00007168142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749863,0.000038945967,0.00054099405,0.0010281033,0.00058274437,0.0003105856],"domain_scores_gemma":[0.9973456,0.0006289026,0.00023164503,0.0010298551,0.00036105627,0.00040290027],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002425629,0.00025347635,0.0005666465,0.0009300187,0.00034596722,0.00026229452,0.0005412681,0.00007052404,0.0013538193],"category_scores_gemma":[0.00042419773,0.0002693927,0.00011191809,0.005589128,0.000088518864,0.0003351978,0.00024019188,0.00018123693,0.000055711174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117446856,0.0023543322,0.03304746,0.00015843142,0.043981563,0.00009583212,0.0004661601,0.62798434,0.0042746626,0.27380025,0.0014095783,0.012309928],"study_design_scores_gemma":[0.0015081275,0.000101533435,0.10053056,0.000011241088,0.103000775,0.000029584802,0.0004083304,0.7045062,0.0021238117,0.08285894,0.0034093368,0.001511555],"about_ca_topic_score_codex":0.0007429587,"about_ca_topic_score_gemma":0.0009397938,"teacher_disagreement_score":0.5862865,"about_ca_system_score_codex":0.00011896231,"about_ca_system_score_gemma":0.00017299214,"threshold_uncertainty_score":0.9999758},"labels":[],"label_agreement":null},{"id":"W2139014051","doi":"10.1016/j.csda.2013.11.017","title":"Efficient optimization of the likelihood function in Gaussian process modelling","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Atlantic Canada Opportunities Agency; Universities Space Research Association","keywords":"Likelihood function; Mathematical optimization; Computer science; Gaussian process; Algorithm; Function (biology); Local optimum; Local search (optimization); Gaussian; Mathematics; Estimation theory","score_opus":0.02169095592741742,"score_gpt":0.27259705880204993,"score_spread":0.2509061028746325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139014051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039015688,0.000050797782,0.9604217,0.000014971267,0.000065606786,0.0001069996,0.00023819381,0.000033730426,0.000052348132],"genre_scores_gemma":[0.6788571,0.0000038930125,0.32028508,0.0000040459204,0.000011321976,0.0000063019766,0.000819017,0.000009139656,0.000004080555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990559,0.000044814344,0.00034181666,0.0001638763,0.00027656255,0.000117000716],"domain_scores_gemma":[0.99928033,0.00015849688,0.000060881695,0.00031527263,0.00014890547,0.000036118774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021100239,0.00009227596,0.00016065795,0.00022084783,0.00004108598,0.000038063925,0.00022413423,0.0000351678,0.00008299586],"category_scores_gemma":[0.0000579491,0.000078849116,0.000033075587,0.0011669479,0.000017811071,0.00008340268,0.000041139225,0.000091264934,0.0000039951274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014587876,0.000016523678,0.0016640117,0.000039004008,0.00012246444,1.284091e-7,0.00006565567,0.9971593,0.0000024258122,0.00032809257,0.000058669208,0.0005422689],"study_design_scores_gemma":[0.00012739793,0.0000032018372,0.016367406,0.000010612393,0.0001492038,1.2854632e-7,0.000012783266,0.9809648,0.000002450467,0.002275073,0.000006469551,0.000080474936],"about_ca_topic_score_codex":0.00012190849,"about_ca_topic_score_gemma":0.000016092057,"teacher_disagreement_score":0.6401366,"about_ca_system_score_codex":0.0000319573,"about_ca_system_score_gemma":0.000021669364,"threshold_uncertainty_score":0.32153738},"labels":[],"label_agreement":null},{"id":"W2145541966","doi":"10.1016/j.csda.2004.06.015","title":"How many principal components? stopping rules for determining the number of non-trivial axes revisited","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":835,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Principal component analysis; Uncorrelated; Variation (astronomy); Variance (accounting); Mathematics; Set (abstract data type); Statistics; Data set; Total variation; Field (mathematics); Computer science; Data mining; Algorithm","score_opus":0.1513757986669602,"score_gpt":0.434713691517873,"score_spread":0.2833378928509128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145541966","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01954719,0.000009743425,0.960999,0.0002927271,0.000029812112,0.00035693092,0.018707816,0.000020987043,0.00003578357],"genre_scores_gemma":[0.213726,0.0000057357875,0.77908206,0.000046171663,0.000073459996,0.00003405138,0.0069871824,0.000017928829,0.000027396689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982384,0.00009204694,0.00057936186,0.0004129932,0.00044992092,0.0002273165],"domain_scores_gemma":[0.9933865,0.004955278,0.00045397977,0.00065809133,0.0004639331,0.000082212566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062303065,0.00018376706,0.00048786832,0.00011201335,0.00031002946,0.00014866343,0.0005886326,0.000048638183,0.00004022797],"category_scores_gemma":[0.0021395434,0.00014698689,0.00012317127,0.00052028784,0.0001691385,0.00011601395,0.00024335657,0.00011312331,0.000006665496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021672526,0.00022413448,0.0050735394,0.00016180327,0.0011566274,0.0000022170543,0.00013427953,0.0031792577,0.000032619126,0.97803503,0.00118744,0.010791379],"study_design_scores_gemma":[0.0006068599,0.00001674506,0.06746955,0.00003327639,0.0020549274,0.0000018363431,0.00003438236,0.35384724,0.000009239905,0.575151,0.0005941453,0.00018077713],"about_ca_topic_score_codex":0.000055411518,"about_ca_topic_score_gemma":0.000021640664,"teacher_disagreement_score":0.402884,"about_ca_system_score_codex":0.000046170884,"about_ca_system_score_gemma":0.00006347923,"threshold_uncertainty_score":0.59939516},"labels":[],"label_agreement":null},{"id":"W2149684740","doi":"10.1016/j.csda.2005.09.010","title":"Automatic dimensionality selection from the scree plot via the use of profile likelihood","year":2005,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Plot (graphics); Heuristic; Computer science; Simple (philosophy); Dimension (graph theory); Curse of dimensionality; Artificial intelligence; Selection (genetic algorithm); Likelihood function; Mathematics; Algorithm; Statistics; Estimation theory","score_opus":0.04932169699503142,"score_gpt":0.28506370484169663,"score_spread":0.2357420078466652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149684740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008121328,0.000088357476,0.9890939,0.0010695688,0.00007955201,0.00010207023,0.0013769388,0.000062356776,0.0000059451227],"genre_scores_gemma":[0.2657496,0.0000054127477,0.7318136,0.00026765777,0.00007767216,0.0000050438985,0.002057667,0.000005271123,0.000018090484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981452,0.00024719723,0.00045320418,0.00041324858,0.00058161415,0.00015948829],"domain_scores_gemma":[0.9970084,0.0014247998,0.0003557511,0.0007452063,0.0004203755,0.000045489323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004600297,0.00012895335,0.00020584179,0.00009507104,0.00044268233,0.00031851575,0.00089892617,0.000034205834,0.00009923765],"category_scores_gemma":[0.0002482202,0.000082599945,0.00006330506,0.001171452,0.00015109399,0.0007414466,0.00035610574,0.00014630491,0.000032460706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008307303,0.00016144285,0.00853659,0.000015370977,0.0012588918,0.0000012576527,0.0003486695,0.14051437,0.000045290115,0.006471806,0.02042952,0.82220846],"study_design_scores_gemma":[0.000097351054,0.000009446226,0.078770325,0.000008433203,0.00045554055,0.0000053352414,0.00000535696,0.9080795,0.000024185589,0.011792335,0.0006606452,0.000091538976],"about_ca_topic_score_codex":0.0010194599,"about_ca_topic_score_gemma":0.00052172045,"teacher_disagreement_score":0.8221169,"about_ca_system_score_codex":0.000037386413,"about_ca_system_score_gemma":0.00020305775,"threshold_uncertainty_score":0.34047994},"labels":[],"label_agreement":null},{"id":"W2152559857","doi":"10.1016/j.csda.2007.07.003","title":"Lifetime analysis based on the generalized Birnbaum–Saunders distribution","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":92,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Applied mathematics; Monte Carlo method; Inference; Goodness of fit; Likelihood function; Statistics; Maximum likelihood; Algorithm; Computer science; Mathematical optimization; Artificial intelligence","score_opus":0.10581504418069003,"score_gpt":0.3962898694052666,"score_spread":0.29047482522457657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152559857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008754415,0.000007766914,0.9506599,0.0016257662,0.00003357371,0.0002595604,0.0461318,0.00010836056,0.00029787648],"genre_scores_gemma":[0.64030266,0.0000032257913,0.23776044,0.0006934626,0.00004730181,0.000023998638,0.121065706,0.000016179698,0.00008704815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967925,0.00022636133,0.0008939679,0.0006597657,0.0010583922,0.00036903698],"domain_scores_gemma":[0.9903103,0.007217527,0.00041832327,0.0012910765,0.00053943915,0.00022334141],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016803854,0.00027399103,0.00048049903,0.00042020375,0.00060880557,0.0001907834,0.0006813418,0.00008528766,0.0019777564],"category_scores_gemma":[0.0026300922,0.00022067061,0.000250554,0.005024789,0.00024301911,0.00009495914,0.00012410861,0.00020960973,0.00015271654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028898488,0.00024457046,0.001353932,0.000009547416,0.002170881,0.00000458281,0.000015914566,0.106082365,0.0000014150978,0.8495813,0.03953864,0.0009679588],"study_design_scores_gemma":[0.00024781819,0.000013519588,0.07128879,0.000003276578,0.0058419066,4.0402358e-7,0.000018576735,0.7825952,0.0000039986803,0.13833934,0.0014414632,0.00020569084],"about_ca_topic_score_codex":0.00013836588,"about_ca_topic_score_gemma":0.00025815587,"teacher_disagreement_score":0.7128994,"about_ca_system_score_codex":0.0001780432,"about_ca_system_score_gemma":0.00011340706,"threshold_uncertainty_score":0.99893457},"labels":[],"label_agreement":null},{"id":"W2160558412","doi":"10.1016/s0167-9473(01)00048-2","title":"A modified score function estimator for multinomial logistic regression in small samples","year":2002,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Mathematics; Statistics; Multinomial logistic regression; Logistic regression; Covariate; Binomial regression; Estimator; Econometrics; Multinomial distribution","score_opus":0.4420553852036066,"score_gpt":0.4284358865853111,"score_spread":0.013619498618295478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160558412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014387369,0.000046392775,0.98698705,0.00007855968,0.0001026712,0.00032495783,0.010925472,0.000047717804,0.00004842046],"genre_scores_gemma":[0.13387704,0.000010097406,0.86084104,0.000042901946,0.00007428188,0.000043710632,0.0050516105,0.000021486525,0.000037840302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977777,0.0001878159,0.00074822735,0.0006709019,0.0003009668,0.00031437635],"domain_scores_gemma":[0.9911646,0.0075447033,0.0003120551,0.0005852234,0.000267226,0.00012618216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005975585,0.000246879,0.00057952036,0.0003533148,0.00019805298,0.00011455375,0.00039789703,0.00009695124,0.00036815737],"category_scores_gemma":[0.006857515,0.00022167082,0.00008744723,0.0006911963,0.0001219861,0.00011109345,0.00016024316,0.00015987606,0.00001673558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013210044,0.00038255338,0.0056716823,0.0002104777,0.0005060133,0.000022300876,0.00010115483,0.016654698,0.0000070340893,0.87790495,0.008805463,0.089601584],"study_design_scores_gemma":[0.0003938,0.000034088192,0.01181404,0.000024882023,0.0006588657,0.0000010744327,0.000008000722,0.5365493,5.374981e-7,0.4503187,0.000053124048,0.00014353872],"about_ca_topic_score_codex":0.0002567216,"about_ca_topic_score_gemma":0.00048567785,"teacher_disagreement_score":0.51989466,"about_ca_system_score_codex":0.00007559775,"about_ca_system_score_gemma":0.000046897447,"threshold_uncertainty_score":0.90394735},"labels":[],"label_agreement":null},{"id":"W2202617390","doi":"10.1016/j.csda.2015.09.007","title":"A nonlinear population Monte Carlo scheme for the Bayesian estimation of parameters of <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si3.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>α</mml:mi></mml:math>-stable distributions","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Office of Naval Research Global; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Ministerio de Economía y Competitividad; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Scroll; Mathematics; Applied mathematics; Monte Carlo method; Nonlinear system; Population; Bayesian probability; Computer science; Algorithm; Statistics; Physics; Engineering","score_opus":0.05707409057324636,"score_gpt":0.33114665828665957,"score_spread":0.2740725677134132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2202617390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35380757,0.00006162879,0.6366877,0.00007185199,0.00008527265,0.00007802323,0.009172331,0.000018421517,0.000017191822],"genre_scores_gemma":[0.4784056,0.000018107246,0.51103806,0.000027661308,0.00005185683,0.00004455112,0.010374725,0.000026153502,0.00001326084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976899,0.00011740639,0.0008455112,0.00039276783,0.00069098093,0.00026344453],"domain_scores_gemma":[0.995565,0.0022419796,0.00085850817,0.0008342972,0.000365606,0.00013461814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012461386,0.00020758875,0.00033512907,0.00013526136,0.00026237956,0.00010828188,0.00042985997,0.00014472853,0.000008050257],"category_scores_gemma":[0.0028976942,0.00020975943,0.00026199222,0.0005228506,0.00016104485,0.0002604958,0.0002690136,0.00015667062,0.0000014213447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000979262,0.00014229876,0.000102527796,0.00020119415,0.0009525571,0.0000048714583,0.00019856975,0.15468602,0.000012507411,0.8406977,0.0012548908,0.0016489443],"study_design_scores_gemma":[0.00044357523,0.000108161024,0.00021166651,0.00006180511,0.0021511281,0.000005954733,0.00017882127,0.9889623,0.00007799068,0.0074346527,0.00019380257,0.00017013562],"about_ca_topic_score_codex":0.0013068314,"about_ca_topic_score_gemma":0.00061176583,"teacher_disagreement_score":0.83427626,"about_ca_system_score_codex":0.00003122572,"about_ca_system_score_gemma":0.0002326831,"threshold_uncertainty_score":0.8553741},"labels":[],"label_agreement":null},{"id":"W2277420127","doi":"10.1016/j.csda.2016.02.007","title":"Special issue on Bayesian econometrics","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bayesian probability; Replicate; Simulated annealing; Computer science; Selection (genetic algorithm); Model selection; Approximate Bayesian computation; Bayesian statistics; Statistics; Mathematics; Data mining; Mathematical optimization; Algorithm; Bayesian inference; Artificial intelligence","score_opus":0.061696752542991465,"score_gpt":0.305885672119435,"score_spread":0.24418891957644356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277420127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003912553,0.000012604575,0.9937601,0.0011541309,0.0003246697,0.00004692551,0.0024903668,0.0000678403,0.0021041997],"genre_scores_gemma":[0.10883978,0.000058260262,0.8855064,0.00073463406,0.0022917904,0.0000047725844,0.0017168849,0.00001406447,0.00083342684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979853,0.00007763334,0.00039756892,0.0007830139,0.000493862,0.00026261737],"domain_scores_gemma":[0.9974403,0.0008700476,0.0001640043,0.0011428627,0.00020815841,0.00017463874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037895888,0.00017437802,0.00027709632,0.00061406544,0.00016239163,0.00027625167,0.0016159207,0.00005077729,0.00084198796],"category_scores_gemma":[0.0002774776,0.00013736014,0.00006569002,0.0016514485,0.00006748696,0.00045401635,0.00044048988,0.00008877096,0.0005866003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061459127,0.000089692105,0.0013031885,0.0000038776075,0.00041139795,0.000020556648,0.000040571926,0.027072946,8.3067823e-7,0.34206146,0.14297064,0.48601872],"study_design_scores_gemma":[0.00019039914,0.000046346428,0.006915951,0.000007615056,0.00015637938,0.0000017383977,0.0000015074736,0.87530375,0.0000025850677,0.08691465,0.030220997,0.00023807042],"about_ca_topic_score_codex":0.000045935725,"about_ca_topic_score_gemma":0.000045563786,"teacher_disagreement_score":0.84823084,"about_ca_system_score_codex":0.00007458494,"about_ca_system_score_gemma":0.00012622934,"threshold_uncertainty_score":0.9219178},"labels":[],"label_agreement":null},{"id":"W2279780363","doi":"10.1016/j.csda.2016.09.009","title":"Estimating functional linear mixed-effects regression models","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics; Statistics; Linear regression; Linear model; Regression; Econometrics; Proper linear model; Regression analysis; Bayesian multivariate linear regression","score_opus":0.16894574410136837,"score_gpt":0.4132596828803319,"score_spread":0.2443139387789635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2279780363","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011793564,0.000030812193,0.9925062,0.0001413994,0.00025038244,0.00012664104,0.005539265,0.00008393901,0.00014198302],"genre_scores_gemma":[0.07484655,0.000007795363,0.922561,0.000075916774,0.00017796902,0.000014909921,0.0021305864,0.000025307017,0.00015995077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724966,0.00029849415,0.00064272486,0.0006855523,0.00082023686,0.00030333688],"domain_scores_gemma":[0.98690146,0.011336115,0.0003289161,0.0007833638,0.00046270044,0.0001874513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150144,0.00025648606,0.0005064874,0.00026111447,0.00025051765,0.00006950343,0.0004341636,0.00008031059,0.0005364274],"category_scores_gemma":[0.0064809765,0.0001716374,0.00009281605,0.0006968871,0.00014508441,0.00027423227,0.0003748076,0.000133154,0.000076005475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028332934,0.00014178267,0.0010753917,0.00009397146,0.000881781,0.000023708568,0.000033059485,0.033941586,0.000028961373,0.83134854,0.023899615,0.1085033],"study_design_scores_gemma":[0.00019606209,0.000017730863,0.0038481138,0.00004704605,0.0006030976,0.0000020101068,0.0000019734675,0.51242787,0.000005978604,0.48266464,0.000048780115,0.00013669604],"about_ca_topic_score_codex":0.000043511263,"about_ca_topic_score_gemma":0.00001939103,"teacher_disagreement_score":0.47848627,"about_ca_system_score_codex":0.00006813738,"about_ca_system_score_gemma":0.00009755366,"threshold_uncertainty_score":0.7758802},"labels":[],"label_agreement":null},{"id":"W2314231116","doi":"10.1016/j.csda.2016.06.007","title":"Functional archetype and archetypoid analysis","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Sustainability and Ecological Systems Analysis","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Archetype; Functional data analysis; Basis (linear algebra); Computer science; Multivariate statistics; Set (abstract data type); Multivariate analysis of variance; Multivariate analysis; Functional dependency; Function (biology); Discretization; Algorithm; Mathematics; Data mining; Machine learning","score_opus":0.03782140878164079,"score_gpt":0.26961890435436675,"score_spread":0.23179749557272597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314231116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07856587,0.000025834133,0.91877794,0.00069952715,0.000019959762,0.000078120385,0.0015793428,0.000029613964,0.00022379932],"genre_scores_gemma":[0.95399576,0.000029127323,0.042171065,0.00014938714,0.00003253929,0.000010527693,0.0028306597,0.000007009304,0.00077390263],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759877,0.00019014545,0.00044949513,0.0008609085,0.0006042764,0.00029641355],"domain_scores_gemma":[0.9977765,0.0011110245,0.00016530845,0.0006618062,0.00007067974,0.00021469286],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008423346,0.0001766539,0.0004329591,0.0002798492,0.0002712721,0.00007411726,0.00036316286,0.00006692557,0.012386581],"category_scores_gemma":[0.00054831273,0.00012324275,0.00016169249,0.0026519003,0.0004030717,0.0002700616,0.0007257639,0.000079371355,0.00032226866],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002289791,0.0000918182,0.8553185,0.000005648422,0.0044296575,0.000009795089,0.000038029888,0.11826733,0.000014505161,0.0034985703,0.004871975,0.013431277],"study_design_scores_gemma":[0.00014576169,0.000017171253,0.7781412,8.9309646e-7,0.004107558,0.0000012849696,0.000019133257,0.19607262,5.913325e-7,0.019171292,0.0021590048,0.00016348378],"about_ca_topic_score_codex":0.0016311877,"about_ca_topic_score_gemma":0.0031473176,"teacher_disagreement_score":0.8766069,"about_ca_system_score_codex":0.00018499393,"about_ca_system_score_gemma":0.000024474653,"threshold_uncertainty_score":0.9885162},"labels":[],"label_agreement":null},{"id":"W2409171482","doi":"10.1016/j.csda.2016.05.021","title":"Median-based estimation of dynamic panel models with fixed effects","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bank of Canada; Wilfrid Laurier University","funders":"","keywords":"Estimator; Outlier; Mathematics; Statistics; Gaussian; Linear model","score_opus":0.05360313135039285,"score_gpt":0.2524925072932777,"score_spread":0.19888937594288486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409171482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004374943,0.00011822856,0.9557858,0.0003003478,0.00003600792,0.0000968395,0.03921037,0.000020393309,0.000057076868],"genre_scores_gemma":[0.7231459,0.00002879539,0.25312957,0.000054986896,0.000011099166,0.000008647343,0.023541221,0.000012894344,0.0000668477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983328,0.00003876475,0.00066895067,0.0005657634,0.0002070113,0.00018672882],"domain_scores_gemma":[0.99720335,0.0011636382,0.00058208994,0.0007640616,0.00019148612,0.00009536075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036368473,0.00017344266,0.00058711023,0.00059250876,0.00008013723,0.000048743583,0.00047009622,0.000054738914,0.0003158695],"category_scores_gemma":[0.00045174576,0.00014012297,0.000089840745,0.0010417706,0.0001196858,0.00035712833,0.00008435581,0.00005267498,0.00010453215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004432341,0.00012619012,0.021001427,0.00007192318,0.0020660555,0.000008883495,0.000037695612,0.8981449,0.000005459164,0.053213414,0.0008102939,0.02446945],"study_design_scores_gemma":[0.00049620646,0.000041174044,0.04985451,0.000017618944,0.0006810107,3.1053477e-7,0.000002002987,0.8651464,0.000004167705,0.08350749,0.000064719665,0.0001843783],"about_ca_topic_score_codex":0.0011342606,"about_ca_topic_score_gemma":0.00059158826,"teacher_disagreement_score":0.718771,"about_ca_system_score_codex":0.00006373171,"about_ca_system_score_gemma":0.00006058627,"threshold_uncertainty_score":0.5714049},"labels":[],"label_agreement":null},{"id":"W2525445790","doi":"10.1016/j.csda.2016.09.007","title":"Model selection for discrete regular vine copulas","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Alexander von Humboldt-Stiftung","keywords":"Vine copula; Copula (linguistics); Bivariate analysis; Univariate; Multivariate statistics; Benchmark (surveying); Computer science; Joint probability distribution; Mathematics; Marginal distribution; Gaussian; Data mining; Algorithm; Mathematical optimization; Econometrics; Statistics; Random variable","score_opus":0.05648152366928197,"score_gpt":0.34696084512182107,"score_spread":0.2904793214525391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525445790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046340232,0.000036520003,0.99468815,0.0009009219,0.00006539609,0.00014211668,0.0040171673,0.000071050184,0.000032327454],"genre_scores_gemma":[0.042049587,0.000017272545,0.955074,0.00018251453,0.00006618137,0.000017127622,0.0021051792,0.000012454196,0.00047565377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816316,0.00009934231,0.00036750062,0.00073848525,0.00038036576,0.00025114868],"domain_scores_gemma":[0.99799275,0.0005448116,0.00017961726,0.0008023771,0.00035837793,0.00012206382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000592355,0.0001652824,0.00029635715,0.00023649003,0.00020529843,0.00014569277,0.0009447124,0.00005252281,0.000022300455],"category_scores_gemma":[0.00021306767,0.00012415813,0.00009518246,0.00075507234,0.000051737527,0.0005442261,0.0003239276,0.000051636056,0.000010426119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013359711,0.000036482023,0.00032884133,0.000012324225,0.0005631025,0.0000014952936,0.00003272764,0.064113274,0.00011487957,0.8239916,0.016688792,0.09410311],"study_design_scores_gemma":[0.00018852575,0.000018237986,0.00048702155,0.0000041338303,0.000281758,0.0000014368333,2.2457019e-7,0.61592925,0.000013594769,0.38231128,0.00064203946,0.00012252106],"about_ca_topic_score_codex":0.0000372876,"about_ca_topic_score_gemma":0.000090230715,"teacher_disagreement_score":0.5518159,"about_ca_system_score_codex":0.000059421294,"about_ca_system_score_gemma":0.00012896684,"threshold_uncertainty_score":0.5063022},"labels":[],"label_agreement":null},{"id":"W2562692326","doi":"10.1016/j.csda.2016.12.007","title":"Hierarchical models: Local proposal variances for RWM-within-Gibbs and MALA-within-Gibbs","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Mathematics; Scaling; Covariance matrix; Applied mathematics; Gaussian; Covariance; Diagonal; Hierarchical database model; Statistics; Mathematical optimization; Statistical physics; Computer science; Physics; Bayesian probability","score_opus":0.1201307406555452,"score_gpt":0.3834520396904838,"score_spread":0.2633212990349386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562692326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014324178,0.000076347635,0.9833002,0.000805436,0.0001581965,0.00037230013,0.013649149,0.00006560737,0.00014032485],"genre_scores_gemma":[0.09987194,0.00004597097,0.89664125,0.0001395044,0.00015530345,0.000044074193,0.0026628945,0.00004139807,0.00039764523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968522,0.00032099982,0.00089875184,0.0009104825,0.0006459425,0.00037158004],"domain_scores_gemma":[0.9934542,0.0046364274,0.00040770398,0.00078065664,0.00046074417,0.00026027273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018829157,0.00032799537,0.00069735973,0.0003046361,0.00027956633,0.00015043498,0.0005592783,0.00012853403,0.000056979967],"category_scores_gemma":[0.00149997,0.00023352134,0.00013101389,0.00047879154,0.00032926575,0.00033731834,0.00043697585,0.0001654443,6.670984e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013078474,0.00014655411,0.00030898326,0.0001653999,0.0015226812,0.000018802837,0.00034866348,0.015612069,0.000012921194,0.9420018,0.006614465,0.033116844],"study_design_scores_gemma":[0.00047176387,0.0000503972,0.0001105326,0.000025155547,0.0010252298,0.000006325849,0.00003556439,0.5571263,0.000006007924,0.44034365,0.0005859312,0.00021318869],"about_ca_topic_score_codex":0.00008675907,"about_ca_topic_score_gemma":0.00061680825,"teacher_disagreement_score":0.54151416,"about_ca_system_score_codex":0.00007242911,"about_ca_system_score_gemma":0.0003360786,"threshold_uncertainty_score":0.95227236},"labels":[],"label_agreement":null},{"id":"W2594897147","doi":"10.1016/j.csda.2018.08.016","title":"Mixtures of generalized hyperbolic distributions and mixtures of skew-t distributions for model-based clustering with incomplete data","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Missing data; Skew; Imputation (statistics); Cluster analysis; Mixture model; Mathematics; Multivariate statistics; Expectation–maximization algorithm; Applied mathematics; Statistics; Algorithm; Computer science; Maximum likelihood","score_opus":0.0639664086196896,"score_gpt":0.34615312516069463,"score_spread":0.282186716541005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594897147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007434064,0.0001451047,0.9127948,0.00020815466,0.000032742908,0.00018715346,0.08585597,0.000023895684,0.000008733645],"genre_scores_gemma":[0.24824314,0.000010179345,0.724441,0.00005284924,0.000035635665,0.000008708591,0.02719633,0.00000815012,0.000004038713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798834,0.00013234523,0.00054551853,0.00072748883,0.00036811407,0.00023817246],"domain_scores_gemma":[0.9965102,0.0006356025,0.00036964135,0.0016638811,0.00069783174,0.00012284369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053791935,0.00020539503,0.0005175046,0.00022352334,0.00028595421,0.00010443593,0.0015143456,0.00005776604,0.000007657991],"category_scores_gemma":[0.00024220867,0.0001785368,0.000060968694,0.0009005922,0.0003917813,0.00031262217,0.00088025734,0.00007995407,3.5313394e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013307456,0.0003232309,0.0012573563,0.00022304775,0.0021547268,0.0000034219202,0.00018798248,0.08890806,0.000654414,0.8706842,0.007186172,0.028284295],"study_design_scores_gemma":[0.00048455273,0.0000675603,0.0024169201,0.000017755261,0.00088646123,0.0000024556543,7.7140214e-7,0.8750671,0.0001372934,0.12051386,0.00023079531,0.00017447765],"about_ca_topic_score_codex":0.00024962833,"about_ca_topic_score_gemma":0.00033309753,"teacher_disagreement_score":0.78615904,"about_ca_system_score_codex":0.000021840879,"about_ca_system_score_gemma":0.00024892643,"threshold_uncertainty_score":0.7280519},"labels":[],"label_agreement":null},{"id":"W2624739645","doi":"10.1016/j.csda.2017.05.012","title":"Special issue on Design of Experiments","year":2017,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Robustness (evolution); Computer science; Covariate; Event (particle physics); Event data; Observational error; Data mining; Econometrics; Statistics; Algorithm; Machine learning; Mathematics","score_opus":0.41748951280374996,"score_gpt":0.5449631452611435,"score_spread":0.12747363245739357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624739645","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032522305,0.000021194726,0.9912878,0.00008277175,0.00043151734,0.00013913731,0.0034190423,0.0000089297855,0.0042843707],"genre_scores_gemma":[0.04715719,0.0000070998817,0.95012015,0.000090193964,0.00089989614,0.000004871891,0.00089839613,0.000012597118,0.000809582],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99549,0.0005124508,0.000841746,0.00078835426,0.0021721562,0.00019530037],"domain_scores_gemma":[0.99281794,0.0032175686,0.0008881834,0.002477089,0.0004657951,0.00013341452],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027355067,0.00018300154,0.0005553711,0.00045602236,0.00046694244,0.0005835916,0.0029680266,0.000050917195,0.004388982],"category_scores_gemma":[0.0055683334,0.00015825979,0.00010226989,0.0005484496,0.0003248312,0.00046909723,0.0007780845,0.00009079808,0.0005434009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028087682,0.0004815145,0.0070377765,0.0000044547614,0.0013653452,0.000046797835,0.00040057916,0.46017215,0.00025550427,0.026450135,0.35809422,0.14541067],"study_design_scores_gemma":[0.00043203542,0.00014568515,0.06112413,0.000006518209,0.00038335982,9.607085e-7,0.000077666504,0.8736442,0.0004708424,0.05257071,0.010895384,0.00024851278],"about_ca_topic_score_codex":0.0001536759,"about_ca_topic_score_gemma":0.000010329122,"teacher_disagreement_score":0.41347206,"about_ca_system_score_codex":0.000045931607,"about_ca_system_score_gemma":0.00009934498,"threshold_uncertainty_score":0.9965211},"labels":[],"label_agreement":null},{"id":"W2754529490","doi":"10.1016/j.csda.2017.08.012","title":"Optimizing two-level orthogonal arrays for simultaneously estimating main effects and pre-specified two-factor interactions","year":2017,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics; Factor (programming language); Orthogonal array; Set (abstract data type); Algorithm; Matrix (chemical analysis); Mathematical optimization; Upper and lower bounds; Applied mathematics; Computer science; Statistics; Taguchi methods; Mathematical analysis","score_opus":0.28302554846404343,"score_gpt":0.5167663804318552,"score_spread":0.23374083196781176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754529490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008434566,0.000045540866,0.9776845,0.000106036045,0.00041494792,0.00039821325,0.012756569,0.000031986252,0.00012766395],"genre_scores_gemma":[0.28407758,0.0000020996542,0.71367264,0.00006493122,0.00014908212,0.000023306258,0.001811292,0.000020844918,0.00017823253],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99591374,0.0003830946,0.00096063624,0.0011846913,0.0012000533,0.00035780546],"domain_scores_gemma":[0.97651607,0.020257095,0.00094195904,0.0014374183,0.00059620215,0.00025126478],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021054659,0.0003114646,0.00068261824,0.00044487568,0.0014895279,0.0020469988,0.001551705,0.000048148282,0.00023755869],"category_scores_gemma":[0.015177713,0.00028578256,0.00014891203,0.0004463021,0.00028717524,0.0009844508,0.0008822556,0.00020353323,0.000029112147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019473972,0.000115250165,0.0018477184,0.000024392493,0.00093043374,0.00004439446,0.00055537967,0.87469125,0.0004637374,0.017027803,0.0013184221,0.102786504],"study_design_scores_gemma":[0.00076806516,0.000054850985,0.021577865,0.000018869505,0.00050803414,0.0000124895905,0.000056025332,0.92454004,0.000042703345,0.051934555,0.00019716554,0.0002893413],"about_ca_topic_score_codex":0.00019700939,"about_ca_topic_score_gemma":0.00038813555,"teacher_disagreement_score":0.27564302,"about_ca_system_score_codex":0.00009349147,"about_ca_system_score_gemma":0.00012792535,"threshold_uncertainty_score":0.9999594},"labels":[],"label_agreement":null},{"id":"W2793872545","doi":"10.1016/j.csda.2018.01.012","title":"Prediction with a flexible finite mixture-of-regressions","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Jenny ja Antti Wihurin Rahasto; Natural Sciences and Engineering Research Council of Canada; Magnus Ehrnroothin Säätiö","keywords":"Covariate; Linear regression; Regression; Mathematics; Regression analysis; Random forest; Predictive power; Nonlinear system; Generalized linear model; Statistics; Linear model; Econometrics; Computer science; Applied mathematics; Artificial intelligence","score_opus":0.053367042984998246,"score_gpt":0.32417006742643023,"score_spread":0.270803024441432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793872545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008912103,0.000059350674,0.99604625,0.00016530181,0.00009229668,0.000078646466,0.003029594,0.000064553904,0.00037491173],"genre_scores_gemma":[0.08193006,0.000011217166,0.915294,0.00012586135,0.000080763595,0.0000042159,0.0024123897,0.000007755098,0.00013377178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982527,0.00013599887,0.0003530341,0.00056388526,0.00050641457,0.00018797161],"domain_scores_gemma":[0.9975164,0.00052018935,0.00023902388,0.0010786214,0.0005315337,0.00011422414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042436577,0.00014815561,0.00028737207,0.0003391629,0.00020532528,0.0001182321,0.00096272444,0.000047493806,0.00007235765],"category_scores_gemma":[0.0001350292,0.00011722459,0.00004854772,0.0018514476,0.0001739863,0.00043123725,0.00037855364,0.00010241051,0.000015672616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057034573,0.0002824112,0.009043006,0.000044782966,0.0025067793,0.000024586261,0.00068388873,0.050865915,0.00003834018,0.76158273,0.03016816,0.14470235],"study_design_scores_gemma":[0.00017948847,0.00009190576,0.013129634,0.000017252081,0.00048950175,0.0000040239574,0.0000018562703,0.89906687,0.000030019699,0.08541395,0.0014524428,0.0001230491],"about_ca_topic_score_codex":0.00008967027,"about_ca_topic_score_gemma":0.00006872013,"teacher_disagreement_score":0.848201,"about_ca_system_score_codex":0.000017702232,"about_ca_system_score_gemma":0.00016643871,"threshold_uncertainty_score":0.47802803},"labels":[],"label_agreement":null},{"id":"W2806096886","doi":"10.1016/j.csda.2018.05.015","title":"Addressing overfitting and underfitting in Gaussian model-based clustering","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Overfitting; Cluster analysis; Maxima and minima; Mixture model; Expectation–maximization algorithm; Context (archaeology); Maxima; Computer science; Nonparametric statistics; Artificial intelligence; Convergence (economics); Machine learning; Gaussian; Mathematics; Mathematical optimization; Algorithm; Pattern recognition (psychology); Artificial neural network; Econometrics; Maximum likelihood; Statistics","score_opus":0.11429489834700153,"score_gpt":0.3791082464019549,"score_spread":0.2648133480549534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806096886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007151477,0.000068679736,0.9983868,0.00021856929,0.00005461393,0.00006556698,0.0002467532,0.000045109726,0.00019877526],"genre_scores_gemma":[0.38808858,0.0000027391304,0.6113294,0.0002563797,0.0000379042,0.0000015537679,0.0002683908,0.0000069773814,0.0000081202015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980463,0.00016305732,0.00043118992,0.0007338703,0.0003386863,0.0002869104],"domain_scores_gemma":[0.998386,0.00050607306,0.00018856663,0.00066067337,0.00014500141,0.00011367646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009871016,0.00016804604,0.0002976695,0.00042185956,0.0002713411,0.00040179293,0.0006840586,0.000053415915,0.00000978838],"category_scores_gemma":[0.00019373008,0.00017436914,0.00003292449,0.00113256,0.000110148314,0.0004920881,0.0006616972,0.00014665656,0.0000029255884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001099856,0.00006291414,0.005947079,0.000059405673,0.00024443193,0.000031910444,0.00070313364,0.6498353,0.000026029225,0.1398163,0.00041792894,0.2028446],"study_design_scores_gemma":[0.00023127797,0.000013192032,0.007734825,0.000033539545,0.00011499547,0.0000021751832,0.000005061083,0.91125613,0.0000041761327,0.080402695,0.000020820424,0.00018109118],"about_ca_topic_score_codex":0.00014784404,"about_ca_topic_score_gemma":0.0004597765,"teacher_disagreement_score":0.38737342,"about_ca_system_score_codex":0.000049350605,"about_ca_system_score_gemma":0.0001437919,"threshold_uncertainty_score":0.7110567},"labels":[],"label_agreement":null},{"id":"W2807119393","doi":"10.1016/j.csda.2018.05.011","title":"Jackknife empirical likelihood method for multiply robust estimation with missing data","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Statistical Sciences Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Jackknife resampling; Empirical likelihood; Estimator; Statistics; Missing data; Mathematics; Econometrics; Context (archaeology); Confidence interval; Maximum likelihood; Estimation; Standard error; Computer science; Engineering","score_opus":0.3159779415801493,"score_gpt":0.5004554349275049,"score_spread":0.18447749334735558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807119393","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010596845,0.000017626287,0.9708123,0.00039662214,0.000066846165,0.00030551388,0.028136348,0.000069694914,0.000089049805],"genre_scores_gemma":[0.003643931,0.000002686809,0.9687529,0.00027005307,0.0001966651,0.000016169572,0.027046297,0.000039396324,0.000031883428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673915,0.00032216264,0.0007687845,0.0010700595,0.0007078028,0.00039203186],"domain_scores_gemma":[0.98555046,0.011105931,0.00041686307,0.0017192333,0.0009802466,0.00022728882],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019822493,0.0002913888,0.0006298834,0.00026050137,0.00041431934,0.0002732165,0.0010875008,0.00008796094,0.00032164826],"category_scores_gemma":[0.009809022,0.00024607635,0.000053927062,0.0010506894,0.0002347976,0.00031922723,0.0005456189,0.00016163941,0.000027325581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034910327,0.0007578748,0.0043972726,0.000385739,0.0049307314,0.000025923695,0.00049022393,0.03285937,0.0000144791375,0.18771671,0.12632856,0.641744],"study_design_scores_gemma":[0.00038337402,0.00010193542,0.004060497,0.000022868795,0.0024086994,0.000004728644,0.000017688262,0.6844216,0.000003880306,0.30763814,0.0007022843,0.00023432248],"about_ca_topic_score_codex":0.00016551712,"about_ca_topic_score_gemma":0.00034709423,"teacher_disagreement_score":0.6515622,"about_ca_system_score_codex":0.000056059293,"about_ca_system_score_gemma":0.00028189804,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W2884300689","doi":"10.1016/j.csda.2018.07.003","title":"Weighted empirical likelihood inference for dynamical correlations","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Inference; Correlation; Confidence interval; Coverage probability; Computation; Dynamical systems theory; Algorithm; Applied mathematics; Interval (graph theory); Statistical physics; Statistics; Computer science; Artificial intelligence; Combinatorics; Physics","score_opus":0.16158646448331299,"score_gpt":0.4697599707420328,"score_spread":0.3081735062587198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884300689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015945821,0.000011141169,0.97724384,0.0002620036,0.00014416946,0.00023153008,0.020167831,0.000074061645,0.00027083032],"genre_scores_gemma":[0.12180768,0.0000038283997,0.8681318,0.00019205309,0.00017992129,0.000025000742,0.009560626,0.000021044028,0.00007803984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975096,0.0001917732,0.000734597,0.0006712856,0.0005279426,0.00036479047],"domain_scores_gemma":[0.98572767,0.011958527,0.00025265478,0.000770748,0.0010708492,0.00021956096],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006969007,0.00022853783,0.00050467695,0.00027960574,0.00041979493,0.00013544841,0.00058440916,0.000105864,0.0009433426],"category_scores_gemma":[0.007864781,0.00021161097,0.00010089991,0.0011973792,0.0003233696,0.00012889713,0.0002888736,0.00017232262,0.00009459195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004211411,0.00026666195,0.010340572,0.000038210936,0.0010721906,0.0000038022274,0.0001429862,0.00030788942,0.0000025767843,0.9256279,0.038946774,0.02320834],"study_design_scores_gemma":[0.00017153849,0.00006199499,0.015979594,0.000005972398,0.0009961913,8.497827e-7,0.000006411192,0.5058042,7.31221e-7,0.47608128,0.00075002556,0.00014120452],"about_ca_topic_score_codex":0.000068464644,"about_ca_topic_score_gemma":0.0003063926,"teacher_disagreement_score":0.5054963,"about_ca_system_score_codex":0.000062871026,"about_ca_system_score_gemma":0.00021995691,"threshold_uncertainty_score":0.99996996},"labels":[],"label_agreement":null},{"id":"W2941373075","doi":"10.1016/j.csda.2019.03.007","title":"Data-driven multistratum designs with the generalized Bayesian <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" display=\"inline\" overflow=\"scroll\" id=\"d1e3469\" altimg=\"si339.gif\"><mml:mi>D</mml:mi></mml:math>-<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" display=\"inline\" overflow=\"scroll\" id=\"d1e3474\" altimg=\"si339.gif\"><mml:mi>D</mml:mi></mml:math> criterion for highly uncertain models","year":2019,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Ministry of Science and Technology, Taiwan","keywords":"Bayesian probability; Bayesian information criterion; Optimal design; Computer science; Algorithm; Class (philosophy); Mathematics; Plot (graphics); Data mining; Artificial intelligence; Statistics; Machine learning","score_opus":0.06620302271394407,"score_gpt":0.33799095240569316,"score_spread":0.2717879296917491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941373075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49757606,0.00039685488,0.48181772,0.00041842845,0.0009045084,0.0003075843,0.01814648,0.00019324201,0.00023911752],"genre_scores_gemma":[0.61881924,0.00024238757,0.34922206,0.0012179271,0.0007021631,0.0005042469,0.028682714,0.00037913697,0.00023011855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9849316,0.0010631541,0.0032170136,0.0037186863,0.0050561866,0.0020133874],"domain_scores_gemma":[0.9831095,0.0068213735,0.0030516817,0.0053069373,0.00072972424,0.0009807958],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0051803915,0.0015058158,0.0013509628,0.0007274118,0.0022265639,0.0031812442,0.0054732705,0.0010871605,0.00030417743],"category_scores_gemma":[0.0025124142,0.001525032,0.0011641172,0.002265005,0.0013796577,0.0032513598,0.003300195,0.0012975191,0.0013805908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013664012,0.0004986141,0.000040349812,0.0002578367,0.0022799263,0.00043429743,0.0008113458,0.19516544,0.0011762055,0.79000837,0.0065453933,0.0014158011],"study_design_scores_gemma":[0.0024898634,0.0010077254,0.0002958336,0.00030753348,0.003037845,0.00024676794,0.0008813384,0.9813035,0.0005854141,0.0045186346,0.0038722495,0.0014533087],"about_ca_topic_score_codex":0.0023052911,"about_ca_topic_score_gemma":0.0013350236,"teacher_disagreement_score":0.78613806,"about_ca_system_score_codex":0.00012211832,"about_ca_system_score_gemma":0.0018503729,"threshold_uncertainty_score":0.9999076},"labels":[],"label_agreement":null},{"id":"W2962842587","doi":"10.1016/j.csda.2018.06.010","title":"Model-based curve registration via stochastic approximation EM algorithm","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Hydrology and Sediment Transport Processes","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Centre National de la Recherche Scientifique","keywords":"Image warping; Dynamic time warping; Smoothing; Inference; Algorithm; Functional data analysis; Curve fitting; Computer science; Image registration; Cluster analysis; Mathematics; Artificial intelligence; Computer vision; Machine learning; Image (mathematics)","score_opus":0.026487786137994622,"score_gpt":0.2813811823188129,"score_spread":0.25489339618081824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962842587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004497762,0.000008919593,0.9932811,0.00008571322,0.00004985479,0.000112471695,0.0017927105,0.000043566553,0.00012790223],"genre_scores_gemma":[0.59814584,8.8982017e-7,0.3825769,0.0001687506,0.0000326483,0.000006991201,0.019006338,0.000006839133,0.000054772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983291,0.000053717475,0.0003589194,0.0005403776,0.0005263617,0.00019149849],"domain_scores_gemma":[0.9990795,0.00013915011,0.00018489864,0.00042632828,0.00008126504,0.00008881843],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037841182,0.0001504546,0.00019042184,0.00010897466,0.00031871235,0.00005340503,0.00037827194,0.00006430354,0.0015226963],"category_scores_gemma":[0.00005911624,0.00015530645,0.000038032413,0.00073273125,0.0002945651,0.00035132855,0.0000756541,0.00009054088,0.00026634496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014508768,0.000096453514,0.0026509436,0.000006066953,0.00015558672,0.0000027834085,0.00010202457,0.97918177,0.000009329156,0.0004674764,0.0020447245,0.015268345],"study_design_scores_gemma":[0.00018483703,0.00004081387,0.0109683685,0.0000021876508,0.00064911746,8.9326124e-7,0.000004614566,0.9662914,0.0000065203167,0.021582881,0.00010684214,0.0001614749],"about_ca_topic_score_codex":0.00017769668,"about_ca_topic_score_gemma":0.0010094037,"teacher_disagreement_score":0.6107042,"about_ca_system_score_codex":0.000058774465,"about_ca_system_score_gemma":0.000051500276,"threshold_uncertainty_score":0.99939007},"labels":[],"label_agreement":null},{"id":"W2963028075","doi":"10.1016/j.csda.2018.12.002","title":"Sparse wavelet estimation in quantile regression with multiple functional predictors","year":2019,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quantile; Quantile regression; Mathematics; Lasso (programming language); Wavelet; Scalar (mathematics); Regression; Rate of convergence; Algorithm; Mathematical optimization; Applied mathematics; Pattern recognition (psychology); Computer science; Artificial intelligence; Statistics","score_opus":0.023073793223642988,"score_gpt":0.2575173982541308,"score_spread":0.23444360503048778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963028075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119986914,0.000036718015,0.878489,0.000011838407,0.00007201719,0.000120512304,0.0010412835,0.00016144397,0.0000802517],"genre_scores_gemma":[0.76118857,0.000011803257,0.22545658,0.000016235028,0.00001627081,0.000004807013,0.013268754,0.000016909633,0.000020063557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879956,0.000035960093,0.0002877476,0.00033095694,0.00038329896,0.00016246807],"domain_scores_gemma":[0.99901557,0.0002916096,0.0000780105,0.00046057446,0.00010319582,0.000051053616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012498362,0.00016296541,0.00025722708,0.0003591035,0.000047199614,0.00005694746,0.00018998189,0.000050627914,0.00016227979],"category_scores_gemma":[0.000048113216,0.0001463125,0.00002922155,0.0006909356,0.000033183594,0.00023722988,0.00007787741,0.00013450332,0.00003344844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023109387,0.000030214434,0.068358235,0.000012920798,0.00028882717,0.000010781939,0.000027505164,0.92327493,0.000030577703,0.0006583242,0.0053741126,0.0019104426],"study_design_scores_gemma":[0.00024519968,0.000017999164,0.18303606,0.000034346827,0.00017449474,0.0000025174143,0.0000078638395,0.81495845,0.000031277326,0.0011415319,0.00020444221,0.00014579463],"about_ca_topic_score_codex":0.00015654617,"about_ca_topic_score_gemma":0.00029759627,"teacher_disagreement_score":0.6530324,"about_ca_system_score_codex":0.00005877602,"about_ca_system_score_gemma":0.000035150148,"threshold_uncertainty_score":0.596645},"labels":[],"label_agreement":null},{"id":"W2991086064","doi":"10.1016/j.csda.2019.106887","title":"A goodness-of-fit test for zero-inflated Poisson mixed effects models in tree abundance studies","year":2019,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Forest ecology and management","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Sampling (signal processing); Goodness of fit; Poisson distribution; Mathematics; Sampling design; Econometrics; Tree (set theory); Computer science","score_opus":0.042117805297380594,"score_gpt":0.31667144506191736,"score_spread":0.2745536397645368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991086064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103675514,0.000104375766,0.89414066,0.00007219278,0.00008934841,0.00043940818,0.0013371224,0.000014265049,0.00012711702],"genre_scores_gemma":[0.86873156,0.000035680663,0.1284602,0.0000682705,0.0000050497783,0.000030364808,0.0024297617,0.000008244121,0.00023086945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986884,0.00005064198,0.0003597448,0.00044991792,0.00025321517,0.00019807876],"domain_scores_gemma":[0.9978751,0.0014582905,0.00019333443,0.00039237906,0.00004098098,0.0000399064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037371655,0.00013419888,0.0003703933,0.00013763561,0.000068898364,0.000016104961,0.00039115717,0.000040405906,0.00010780836],"category_scores_gemma":[0.00028437676,0.00013151387,0.000047503414,0.0006912618,0.0001307803,0.00023189536,0.00040853114,0.000058225247,0.000080051446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026532598,0.00016853277,0.09664571,0.0000841634,0.00059401465,0.0000056761196,0.00011353115,0.8723309,0.000017273329,0.022217212,0.005809106,0.0019873325],"study_design_scores_gemma":[0.00038510974,0.000057309513,0.3154059,0.000008970299,0.00034779258,1.3972164e-7,0.000011573646,0.5916385,0.000004296618,0.09194357,0.000105521685,0.00009128327],"about_ca_topic_score_codex":0.00032694204,"about_ca_topic_score_gemma":0.0026517035,"teacher_disagreement_score":0.76568043,"about_ca_system_score_codex":0.000103769155,"about_ca_system_score_gemma":0.000013692397,"threshold_uncertainty_score":0.536298},"labels":[],"label_agreement":null},{"id":"W3026103209","doi":"10.1016/j.csda.2020.107007","title":"Competing risk modeling and testing for X-chromosome genetic association","year":2020,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Hong Kong Polytechnic University; Research Grants Council, University Grants Committee; National Natural Science Foundation of China; University of International Business and Economics","keywords":"Population; Skewness; Genetic association; Chromosome; Asymptotic distribution; Statistics; Multiple comparisons problem; Genetic model; Mathematics; Computer science; Econometrics; Genetics; Biology; Estimator; Medicine; Single-nucleotide polymorphism; Genotype","score_opus":0.049874999488916695,"score_gpt":0.3052781933639029,"score_spread":0.25540319387498617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026103209","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20134918,0.00018770357,0.7936781,0.00024442223,0.000021112914,0.000100209756,0.004397998,0.000009981214,0.000011304749],"genre_scores_gemma":[0.54534876,0.000050191265,0.44530714,0.00024360375,0.00014257348,0.0000067744995,0.008884395,0.00000982196,0.00000677137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985877,0.00014045346,0.0003945458,0.0005197285,0.00015161873,0.00020591886],"domain_scores_gemma":[0.99844927,0.00056005333,0.0003342283,0.00020937808,0.00034356702,0.00010352181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051803095,0.00012617983,0.00025906082,0.00004837144,0.0002480094,0.000051629984,0.00018891286,0.000086629465,0.000008365692],"category_scores_gemma":[0.0046675242,0.00014126855,0.00005175563,0.00027194008,0.000023058537,0.000005621895,0.00022968256,0.000075457945,0.0000036991619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008127381,0.000012232938,0.32129553,0.000013198186,0.0007662858,4.2388004e-7,0.000041856027,0.67317677,0.00019211769,0.00006523076,0.0012769258,0.0031513239],"study_design_scores_gemma":[0.0002536133,0.000070618094,0.09269638,0.0000016916109,0.0008845877,6.814316e-7,0.000029118022,0.9038496,0.0000023710147,0.0016989476,0.00037303855,0.00013932344],"about_ca_topic_score_codex":0.00012817232,"about_ca_topic_score_gemma":0.00007816397,"teacher_disagreement_score":0.34837094,"about_ca_system_score_codex":0.000023463375,"about_ca_system_score_gemma":0.000067443354,"threshold_uncertainty_score":0.57607645},"labels":[],"label_agreement":null},{"id":"W3092170770","doi":"10.1016/j.csda.2020.107108","title":"Functional time series model identification and diagnosis by means of auto- and partial autocorrelation analysis","year":2020,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Actua","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autocorrelation; Partial autocorrelation function; Autocovariance; Autoregressive model; Series (stratigraphy); Autocorrelation technique; Time series; White noise; Mathematics; Moving-average model; Computer science; Algorithm; Econometrics; Statistics; Autoregressive integrated moving average","score_opus":0.047871864609788824,"score_gpt":0.23676136223225477,"score_spread":0.18888949762246596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092170770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064647472,0.00059384905,0.96427274,0.0008136423,0.000017274904,0.00011305071,0.027648965,0.000022741067,0.000053016527],"genre_scores_gemma":[0.93733346,0.00018104904,0.03406588,0.000084650426,0.000039334336,0.00002300345,0.027917914,0.000015798865,0.00033891053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979236,0.000040404953,0.0010237744,0.0007121187,0.0001578798,0.00014222052],"domain_scores_gemma":[0.99845624,0.00019342234,0.00070385734,0.00036136614,0.00015010069,0.00013500878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038449586,0.0001718118,0.0007184012,0.0004305904,0.00018768269,0.00016220211,0.00018557084,0.000060114377,0.00090777787],"category_scores_gemma":[0.00018940722,0.00020680731,0.00013350912,0.0016898887,0.00012239444,0.0004726616,0.00018978045,0.0000742492,0.00004137413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031011386,0.0000702876,0.14711036,0.00004949196,0.00778703,8.9182157e-7,0.00032741603,0.72520626,0.000012492439,0.10862591,0.009818679,0.00096018345],"study_design_scores_gemma":[0.00016284727,0.00002105741,0.10479231,0.0000015920882,0.0027798729,3.3854784e-7,0.000018125113,0.88138807,0.0000017378508,0.009529091,0.0011304357,0.00017451201],"about_ca_topic_score_codex":0.00062142237,"about_ca_topic_score_gemma":0.00009861493,"teacher_disagreement_score":0.9308687,"about_ca_system_score_codex":0.00002833947,"about_ca_system_score_gemma":0.000023645936,"threshold_uncertainty_score":0.9939531},"labels":[],"label_agreement":null},{"id":"W3092876711","doi":"10.1016/j.csda.2020.107114","title":"Efficient and robust estimation of regression and scale parameters, with outlier detection","year":2020,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Outlier; Robust regression; Regression; Scale (ratio); Mathematics; Statistics; Estimation; Regression analysis; Anomaly detection; Computer science; Artificial intelligence; Pattern recognition (psychology); Geography","score_opus":0.12589472609836827,"score_gpt":0.38811831539139485,"score_spread":0.2622235892930266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092876711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03772738,0.0000381689,0.9601357,0.000081075814,0.0000080821665,0.00012104807,0.0018634916,0.000017737122,0.0000073067763],"genre_scores_gemma":[0.3538461,0.000006934583,0.64569026,0.000023988783,0.000005413185,0.0000023739653,0.00041478637,0.0000076098495,0.0000025091706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988024,0.000092367256,0.00031903267,0.00038188128,0.00030301476,0.0001012674],"domain_scores_gemma":[0.99807924,0.0012328932,0.00022186094,0.00020645402,0.00013923239,0.00012030188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022309275,0.00012585073,0.00033274328,0.000087159366,0.00009860116,0.00003366392,0.00008243208,0.00003279945,0.000011032279],"category_scores_gemma":[0.0007313369,0.000099241784,0.000017475337,0.0003594939,0.00013791153,0.00006312806,0.00012091949,0.00008099208,5.639933e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080003505,0.000048855196,0.00047195403,0.00013795403,0.00027346672,0.000003793065,0.0002777172,0.9215115,0.000020045238,0.014238023,0.00007513712,0.0628616],"study_design_scores_gemma":[0.00025739442,0.000079062884,0.003170428,0.000019710553,0.0010362401,0.0000023246762,0.000037042722,0.9145854,0.000021184587,0.080680706,0.000004583187,0.00010589637],"about_ca_topic_score_codex":0.000028947288,"about_ca_topic_score_gemma":0.000030672494,"teacher_disagreement_score":0.31611872,"about_ca_system_score_codex":0.000011931625,"about_ca_system_score_gemma":0.000018422874,"threshold_uncertainty_score":0.40469626},"labels":[],"label_agreement":null},{"id":"W3151920332","doi":"10.1016/j.csda.2021.107246","title":"A kernel-based measure for conditional mean dependence","year":2021,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Mathematics; Statistics; Applied mathematics; Kernel method; Estimator; Kernel (algebra); Test statistic; Statistical hypothesis testing; Discrete mathematics; Artificial intelligence; Computer science","score_opus":0.19253971489701055,"score_gpt":0.4305250616541861,"score_spread":0.23798534675717553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151920332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023053763,0.000055083783,0.9491734,0.00021364877,0.000059077473,0.00014524518,0.04995375,0.000041377534,0.0001278997],"genre_scores_gemma":[0.10347874,0.000002555702,0.8604081,0.0002813223,0.00007007292,0.00002983474,0.035626106,0.00001936999,0.0000838883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974241,0.00024432145,0.0005740768,0.0006882491,0.00080003985,0.0002692057],"domain_scores_gemma":[0.9888049,0.008646537,0.0002327264,0.00070931565,0.0014397654,0.00016679968],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084239186,0.0002045443,0.0004802034,0.00015894305,0.00024055634,0.00014921391,0.00043890055,0.000071313814,0.0012962923],"category_scores_gemma":[0.007988817,0.00020854764,0.00013219242,0.00082625163,0.00012625662,0.00009878755,0.0001524719,0.00013928872,0.000024449664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028806033,0.00021750621,0.001493357,0.00010395983,0.0012290793,0.000042120457,0.000033511045,0.0127906455,0.000015034444,0.9564056,0.021194274,0.0064461445],"study_design_scores_gemma":[0.00028795408,0.00001606974,0.004870515,0.000009113923,0.0012516013,0.0000029222238,0.0000104760375,0.47727636,0.000017797493,0.51561683,0.000488252,0.00015214666],"about_ca_topic_score_codex":0.0000377062,"about_ca_topic_score_gemma":0.0003480008,"teacher_disagreement_score":0.4644857,"about_ca_system_score_codex":0.00005811308,"about_ca_system_score_gemma":0.0005058253,"threshold_uncertainty_score":0.9996167},"labels":[],"label_agreement":null},{"id":"W3154627384","doi":"10.1016/j.csda.2021.107244","title":"In the pursuit of sparseness: A new rank-preserving penalty for a finite mixture of factor analyzers","year":2021,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Actua","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Rank (graph theory); Factor (programming language); Cluster analysis; Extension (predicate logic); Mathematics; Mixture model; Computer science; Applied mathematics; Algorithm; Mathematical optimization; Statistics; Combinatorics","score_opus":0.059055276069333085,"score_gpt":0.35002857896041284,"score_spread":0.29097330289107975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154627384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015133183,0.00051145646,0.97841644,0.00052632845,0.00003450181,0.00010039408,0.0052525643,0.0000012357693,0.000023909932],"genre_scores_gemma":[0.89150685,0.00015164757,0.08382999,0.00028987127,0.000071061346,0.000011028994,0.023930635,0.000008671705,0.00020023446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883026,0.00010680063,0.00034258582,0.000313301,0.00030933152,0.00009772241],"domain_scores_gemma":[0.9986035,0.00023182473,0.00022888886,0.00059031736,0.0003088109,0.000036610927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025040022,0.000088123394,0.00020919275,0.000109259025,0.00003719456,0.000030327934,0.00056150527,0.000051510036,0.00012725826],"category_scores_gemma":[0.00050916336,0.000074093936,0.00009193627,0.00064831873,0.000038251277,0.000008536578,0.00016692589,0.000044958764,4.5123411e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005273236,0.0006730943,0.032314222,0.00044971323,0.0044337376,0.000014795769,0.0012645209,0.5224868,0.13427909,0.007679346,0.28004366,0.01583367],"study_design_scores_gemma":[0.0031156377,0.00018480455,0.2231139,0.000070778886,0.0028307985,0.0000056398467,0.00094797736,0.64452696,0.020242417,0.019312775,0.08502453,0.0006237694],"about_ca_topic_score_codex":0.00012033251,"about_ca_topic_score_gemma":0.0005170683,"teacher_disagreement_score":0.89458644,"about_ca_system_score_codex":0.0000073047154,"about_ca_system_score_gemma":0.00028379448,"threshold_uncertainty_score":0.30214632},"labels":[],"label_agreement":null},{"id":"W3161171","doi":"10.1016/j.csda.2007.07.001","title":"Total Least Squares and Errors-in-variables Modeling","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Mathematics; Gaussian; Mean squared error; Statistics; Least-squares function approximation; Independent and identically distributed random variables; Observational error; Algorithm; Applied mathematics; Random variable","score_opus":0.08102025011449583,"score_gpt":0.3668163791881038,"score_spread":0.28579612907360796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015798809,0.000085853346,0.980338,0.00007421325,0.000040970717,0.00008086357,0.0034107326,0.0000335701,0.00013701527],"genre_scores_gemma":[0.35955697,0.000009658944,0.63802207,0.000039444403,0.000046554862,0.0000019604354,0.0022623648,0.000012279541,0.000048655795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803567,0.000056421504,0.0006107248,0.0005033694,0.0004779695,0.0003158168],"domain_scores_gemma":[0.9969036,0.0023345111,0.000110389585,0.0003337636,0.0001542222,0.00016351901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006715168,0.00018238559,0.00041990727,0.00028610544,0.00012704021,0.00007818252,0.0002304962,0.000056779012,0.00019669397],"category_scores_gemma":[0.00093988836,0.00017106251,0.000041257088,0.00086284056,0.00009768107,0.00014392138,0.00025178344,0.0001594221,0.000013051796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010953381,0.0005349621,0.014260409,0.0001558241,0.0013843144,0.00020340944,0.0003702041,0.22205083,0.00000847153,0.7014375,0.0028531216,0.056631453],"study_design_scores_gemma":[0.00017908067,0.000014627111,0.016548228,0.000007897309,0.00038815537,0.000005045498,0.000045901263,0.66604954,3.492207e-7,0.3165894,0.000028546321,0.00014322715],"about_ca_topic_score_codex":0.0007748427,"about_ca_topic_score_gemma":0.0004966724,"teacher_disagreement_score":0.44399872,"about_ca_system_score_codex":0.00004432341,"about_ca_system_score_gemma":0.00004131855,"threshold_uncertainty_score":0.6975727},"labels":[],"label_agreement":null},{"id":"W3204055613","doi":"10.1016/j.csda.2022.107553","title":"Empirical likelihood inference for longitudinal data with covariate measurement errors: An application to the LEAN study","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China; University of South Carolina","keywords":"Covariate; Replicate; Estimator; Statistics; Observational error; Mathematics; Inference; Analysis of covariance; Covariance; Econometrics; Computer science; Artificial intelligence","score_opus":0.20546673617862457,"score_gpt":0.42111908182828806,"score_spread":0.21565234564966348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204055613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007083483,0.00006480844,0.9665393,0.0024176633,0.000031198928,0.001123276,0.022696957,0.00003713914,0.0000061398846],"genre_scores_gemma":[0.8171931,0.0000045437096,0.118337505,0.0006847203,0.00012624888,0.00029723745,0.06333148,0.00001927588,0.0000059015942],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970534,0.00008158169,0.00038613833,0.00084567704,0.0014166943,0.00021650997],"domain_scores_gemma":[0.9971979,0.00037702764,0.0001534854,0.0013915247,0.0007271593,0.00015290345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013903838,0.00016358962,0.00034779598,0.00014197215,0.00071034447,0.00006407091,0.00080066774,0.000013313967,0.00006202711],"category_scores_gemma":[0.0003026695,0.00012222286,0.000035350913,0.0010491371,0.000047337227,0.00010605232,0.0010196548,0.0001464899,0.000006674512],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019500415,0.006668731,0.51661146,0.000079467995,0.009472613,0.000042406984,0.00072868855,0.31723905,0.0000043307555,0.006121607,0.13006522,0.011016356],"study_design_scores_gemma":[0.0011927371,0.001162627,0.47988397,0.0000048787456,0.00439618,0.0000055443065,0.0006259729,0.49436125,9.26565e-8,0.0035754542,0.014617116,0.00017415125],"about_ca_topic_score_codex":0.00082166493,"about_ca_topic_score_gemma":0.0047443537,"teacher_disagreement_score":0.8482018,"about_ca_system_score_codex":0.00015158408,"about_ca_system_score_gemma":0.00025954927,"threshold_uncertainty_score":0.5463467},"labels":[],"label_agreement":null},{"id":"W3212684135","doi":"10.1016/j.csda.2021.107400","title":"Flexible quantile contour estimation for multivariate functional data: Beyond convexity","year":2021,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; King Abdullah University of Science and Technology","keywords":"Quantile; Multivariate statistics; Univariate; Mathematics; Bivariate analysis; Estimator; Statistics; Econometrics; Nonparametric statistics; Functional data analysis","score_opus":0.35470927818694936,"score_gpt":0.49593536021661544,"score_spread":0.14122608202966608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212684135","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000666077,0.00007190338,0.90261436,0.0002064147,0.00019942177,0.00024203904,0.09644482,0.000069140755,0.00008531081],"genre_scores_gemma":[0.010055507,0.00001168055,0.8489224,0.00017224651,0.000113601905,0.000025023834,0.14028445,0.000028741608,0.000386403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699306,0.00022380153,0.00079092867,0.0010558508,0.0006157941,0.00032056455],"domain_scores_gemma":[0.98903567,0.007956897,0.00037147242,0.0014283154,0.0010380646,0.0001696126],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010767982,0.00025419702,0.00064219756,0.00014857417,0.00036809343,0.00016676354,0.0005283568,0.00008615333,0.00049125135],"category_scores_gemma":[0.007448455,0.00026328673,0.00009338826,0.00062918477,0.0001195978,0.000518978,0.0005826298,0.00016182568,0.000020675285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006816266,0.0002701497,0.00014940639,0.00012305021,0.0016083281,0.00001657719,0.00003915903,0.14268053,0.00002578819,0.8084388,0.030022493,0.016557582],"study_design_scores_gemma":[0.0004309321,0.00001238249,0.0012513686,0.000006319961,0.0014064222,0.0000027576225,0.000015179889,0.5219297,0.000009530007,0.47356293,0.0012139414,0.00015859243],"about_ca_topic_score_codex":0.00007978037,"about_ca_topic_score_gemma":0.00019808486,"teacher_disagreement_score":0.37924913,"about_ca_system_score_codex":0.00006264255,"about_ca_system_score_gemma":0.00032722083,"threshold_uncertainty_score":0.99998194},"labels":[],"label_agreement":null},{"id":"W323170945","doi":"10.1016/j.csda.2013.03.019","title":"Nonparametric meta-analysis of independent samples of records","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Nonparametric statistics; Quantile; Sample (material); Statistics; Confidence interval; Mathematics; Population; Econometrics; Medicine","score_opus":0.13473331688474383,"score_gpt":0.3399723815747199,"score_spread":0.20523906468997605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W323170945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022055155,0.00021512655,0.9924178,0.00021845858,0.000021197786,0.00013725122,0.0047181444,0.000018725974,0.000047749523],"genre_scores_gemma":[0.51770735,0.000024092871,0.47883213,0.000060275626,0.0000070700426,0.000015599311,0.0033148595,0.0000037135042,0.00003491511],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975704,0.00011812496,0.0008354519,0.00058447156,0.00071881973,0.00017271125],"domain_scores_gemma":[0.9955693,0.0015250932,0.00065173715,0.0014737581,0.00068023417,0.00009991725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039412064,0.00015672666,0.0009974432,0.0011592157,0.0000820149,0.00011565017,0.0016609416,0.000039564213,0.00072742574],"category_scores_gemma":[0.000116559764,0.00013422084,0.0005004074,0.009308012,0.00008475583,0.00035817362,0.0006039688,0.0000881693,0.000019451942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013402635,0.00018061858,0.0067459093,0.000011525924,0.15812421,0.000001093766,0.000038040147,0.71195173,0.00000947735,0.10971877,0.0048446,0.008372685],"study_design_scores_gemma":[0.000043933116,0.0000133736885,0.10797166,3.5796066e-7,0.101484396,2.7429118e-7,0.0000033868184,0.7707313,0.00000584223,0.019518536,0.00012490834,0.0001020407],"about_ca_topic_score_codex":0.002611546,"about_ca_topic_score_gemma":0.00037356315,"teacher_disagreement_score":0.51550186,"about_ca_system_score_codex":0.000016925542,"about_ca_system_score_gemma":0.00006295134,"threshold_uncertainty_score":0.7964802},"labels":[],"label_agreement":null},{"id":"W4205927369","doi":"10.1016/j.csda.2021.107419","title":"Distributed adaptive Huber regression","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regression; Regression analysis; Multivariate adaptive regression splines; Statistics; Econometrics; Computer science; Mathematics; Nonparametric regression","score_opus":0.07218353233010939,"score_gpt":0.36902733490824713,"score_spread":0.29684380257813775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205927369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01154703,0.00027554875,0.949594,0.00037108446,0.000073997944,0.00026304406,0.037571575,0.000051547766,0.0002521359],"genre_scores_gemma":[0.7249914,0.000020793226,0.105084635,0.00015407392,0.00007702481,0.00004669252,0.16862513,0.00002554723,0.0009747307],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704605,0.0002563118,0.0004268364,0.00055530114,0.0014682265,0.0002472468],"domain_scores_gemma":[0.9977966,0.00061615976,0.00018131039,0.00086090545,0.0003714543,0.00017355256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006046893,0.00014657476,0.00043606682,0.00040146254,0.00039039322,0.000039412258,0.00041136116,0.000028848865,0.002372532],"category_scores_gemma":[0.00034951864,0.0001318267,0.00009050527,0.001811046,0.00008137789,0.00008062,0.0009278571,0.00027658854,0.00006891684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069519604,0.0007658666,0.2626105,0.00018163658,0.00844346,0.0011500454,0.00052488915,0.17135282,0.00002616633,0.015360446,0.5336513,0.0052377144],"study_design_scores_gemma":[0.0008658905,0.00010455544,0.03053558,0.0000220291,0.0018613876,0.0005560203,0.0003291614,0.9521634,0.00000127955,0.0036239922,0.009772009,0.00016468384],"about_ca_topic_score_codex":0.00022415395,"about_ca_topic_score_gemma":0.000028194216,"teacher_disagreement_score":0.8445094,"about_ca_system_score_codex":0.00029453638,"about_ca_system_score_gemma":0.000306654,"threshold_uncertainty_score":0.99853945},"labels":[],"label_agreement":null},{"id":"W4221129258","doi":"10.1016/j.csda.2022.107481","title":"Bayesian linear models for cardinal paired comparison data","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Bayesian probability; Statistics; Econometrics","score_opus":0.3913131843259114,"score_gpt":0.49823175051072865,"score_spread":0.10691856618481727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221129258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020869584,0.00007965082,0.825653,0.00013400712,0.00009737471,0.00032336812,0.17356595,0.000060637398,0.000065152235],"genre_scores_gemma":[0.034704547,0.000006710924,0.8603417,0.00011395311,0.0000949956,0.00006429612,0.10449119,0.000041442636,0.00014111846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963598,0.00037805084,0.00088328315,0.0010875942,0.0009082839,0.00038298895],"domain_scores_gemma":[0.9920551,0.005118441,0.00039489934,0.0019454052,0.0003040742,0.00018208912],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016267273,0.0002617501,0.00080604956,0.00023739901,0.00074246083,0.00007428978,0.0015504664,0.000041759333,0.0002625353],"category_scores_gemma":[0.0014425907,0.00028208824,0.00011331029,0.0007532981,0.00009560378,0.0003140065,0.001848158,0.0002630793,0.0000030285107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058991245,0.00019180341,0.00012031606,0.000047623846,0.0010991549,0.000009069978,0.000081967606,0.64284843,6.555681e-7,0.3043476,0.0403292,0.010865164],"study_design_scores_gemma":[0.0002586743,0.00003889469,0.000048451435,0.0000020140776,0.0016792009,0.0000018769957,0.000049300303,0.5346362,1.4430677e-7,0.459266,0.0038425715,0.0001766733],"about_ca_topic_score_codex":0.00012724038,"about_ca_topic_score_gemma":0.00011700436,"teacher_disagreement_score":0.1549184,"about_ca_system_score_codex":0.00010418981,"about_ca_system_score_gemma":0.00017824593,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4225410102","doi":"10.1016/j.csda.2022.107507","title":"Thresholding tests based on affine LASSO to achieve non-asymptotic nominal level and high power under sparse and dense alternatives in high dimension","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Mathematics; Estimator; Nonparametric statistics; Affine transformation; Lasso (programming language); Statistical hypothesis testing; Statistics; Applied mathematics; Thresholding; Artificial intelligence; Computer science","score_opus":0.10754759677286596,"score_gpt":0.3763812355774646,"score_spread":0.26883363880459865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225410102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2711604,0.000009672333,0.72148573,0.0003659085,0.000046508034,0.00014632846,0.006760105,0.000010754849,0.000014593415],"genre_scores_gemma":[0.5348195,0.0000022622673,0.4640222,0.00027857468,0.0000107873,0.0000105887575,0.00082566956,0.000012942591,0.000017523666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977183,0.00027495116,0.0004685714,0.00067067274,0.0006159288,0.00025158157],"domain_scores_gemma":[0.9930694,0.0060534957,0.00017861651,0.0004151266,0.00012517329,0.00015820615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080236926,0.00023278165,0.00048101184,0.00051141484,0.0002441365,0.00010317198,0.0002593897,0.000032361317,0.00034653847],"category_scores_gemma":[0.0012902648,0.00022857643,0.000026562442,0.0007400963,0.00008937165,0.00007912877,0.00060246815,0.00023192322,0.000004748411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037561796,0.00065431796,0.024160292,0.00006342269,0.0005462391,0.00016185157,0.00036225456,0.4957731,0.00010392848,0.46655345,0.002081904,0.009163608],"study_design_scores_gemma":[0.0004778303,0.00020349446,0.30323446,0.000021250333,0.00027434013,0.000002656873,0.00003712305,0.520949,0.0000026534099,0.1746108,0.000009767805,0.00017659705],"about_ca_topic_score_codex":0.000608104,"about_ca_topic_score_gemma":0.0003179632,"teacher_disagreement_score":0.29194266,"about_ca_system_score_codex":0.000115903895,"about_ca_system_score_gemma":0.00007259921,"threshold_uncertainty_score":0.9321077},"labels":[],"label_agreement":null},{"id":"W4245729715","doi":"10.1016/j.csda.2010.05.023","title":"The Fifth Special Issue on Computational Econometrics","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Econometrics; Mathematics; Mathematical economics; Applied mathematics; Computer science","score_opus":0.17515481253798562,"score_gpt":0.4302398884018205,"score_spread":0.2550850758638349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245729715","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019102312,0.000008757961,0.98127997,0.0020230624,0.0003551428,0.00015165248,0.011420767,0.000046402558,0.0028040125],"genre_scores_gemma":[0.19849819,0.000016370088,0.78192437,0.0006038266,0.002424558,0.000024324381,0.01514806,0.000023170753,0.0013371133],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966158,0.00009992833,0.0008312602,0.0007346264,0.0014837175,0.00023466558],"domain_scores_gemma":[0.98741513,0.009831614,0.00045692967,0.0013883779,0.0007643518,0.00014361959],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024082481,0.00016713241,0.0002817099,0.0006122656,0.00095794373,0.0009285124,0.0021513014,0.00006202192,0.0030792747],"category_scores_gemma":[0.0043527684,0.00011971447,0.00011211135,0.0033753435,0.00029715287,0.0001805028,0.0004648385,0.00031506398,0.0011640857],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008800843,0.00007078397,0.0027939533,7.140963e-7,0.0001624542,0.000002217796,0.000034204008,0.15806976,2.25373e-7,0.30163196,0.4179132,0.119311735],"study_design_scores_gemma":[0.000048285285,0.00001257907,0.024251048,4.5403254e-7,0.000073967494,0.0000012169204,0.000007835082,0.43341184,2.0988082e-7,0.2523331,0.2897826,0.00007686916],"about_ca_topic_score_codex":0.000089378176,"about_ca_topic_score_gemma":0.000685931,"teacher_disagreement_score":0.27534208,"about_ca_system_score_codex":0.00003225028,"about_ca_system_score_gemma":0.0001428958,"threshold_uncertainty_score":0.99961364},"labels":[],"label_agreement":null},{"id":"W4252277490","doi":"10.1016/j.csda.2005.06.002","title":"Point and interval estimation for the two-parameter Birnbaum–Saunders distribution based on Type-II censored samples","year":2005,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Estimator; Monte Carlo method; Statistics; Mathematics; M-estimator; Confidence interval; Point estimation; Interval estimation; Maximum likelihood sequence estimation; Applied mathematics","score_opus":0.1153404177040983,"score_gpt":0.4046151108205764,"score_spread":0.2892746931164781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252277490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006020082,0.0000143525795,0.95487136,0.0033075826,0.00004119366,0.0004070641,0.040673666,0.00006200835,0.000020769141],"genre_scores_gemma":[0.44976205,0.0000038653766,0.50179315,0.00034687636,0.00003538226,0.00004377,0.047975976,0.000011212382,0.000027739954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983048,0.000087688364,0.0005416985,0.0004551503,0.00040360962,0.0002070663],"domain_scores_gemma":[0.9923185,0.006344412,0.00024883926,0.0005722389,0.00040905198,0.00010696765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049273047,0.0001973685,0.00027903522,0.000114469694,0.0006144443,0.00016271629,0.00028891515,0.000047610396,0.00028736313],"category_scores_gemma":[0.0035739404,0.00016039565,0.000077245015,0.00059244805,0.00018957994,0.0001451909,0.00010859752,0.00011398949,0.000024105118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005455915,0.00018944222,0.00010179585,0.000025863537,0.00033759067,2.902319e-7,0.000035620134,0.20680031,0.0000015254511,0.73178345,0.037574623,0.023094928],"study_design_scores_gemma":[0.00047202437,0.000044966306,0.008590932,0.00000849714,0.0011347346,0.0000010804395,0.000018044166,0.82684106,0.0000042074594,0.16042383,0.002310053,0.00015056717],"about_ca_topic_score_codex":0.000046620476,"about_ca_topic_score_gemma":0.0000931002,"teacher_disagreement_score":0.6200408,"about_ca_system_score_codex":0.00011638454,"about_ca_system_score_gemma":0.0000686844,"threshold_uncertainty_score":0.6540745},"labels":[],"label_agreement":null},{"id":"W4285498631","doi":"10.1016/j.csda.2022.107567","title":"High-dimensional robust regression with L-loss functions","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Outlier; Estimator; Robust regression; Least absolute deviations; Quantile regression; Robust statistics; Robustness (evolution); Regression; Penalty method; Quantile; Sample size determination; Applied mathematics; Regression analysis; Smoothness; Mathematical optimization; Statistics; Algorithm","score_opus":0.1353971684618698,"score_gpt":0.40104529412779705,"score_spread":0.2656481256659272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285498631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011940342,0.00003202765,0.96677387,0.000225722,0.00011037432,0.00014822897,0.031405747,0.000067591696,0.000042408694],"genre_scores_gemma":[0.059778035,0.0000032023981,0.9146088,0.00014121525,0.00005431876,0.000043530625,0.024701834,0.000031980475,0.0006371038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970673,0.0003274491,0.00049698807,0.0007295491,0.0010967692,0.00028195843],"domain_scores_gemma":[0.9958364,0.0025953664,0.00030942628,0.0008072358,0.00029134154,0.00016023075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006141712,0.00023409679,0.0004813157,0.00027484054,0.00092934974,0.000053377487,0.00043306896,0.000030519917,0.0019081277],"category_scores_gemma":[0.0004964905,0.00019618074,0.00006589624,0.0011469299,0.00013773113,0.00016469439,0.0006623945,0.0003168391,0.000009768482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078888035,0.00019810145,0.00033955305,0.00001486206,0.0007549648,0.00006994109,0.000027340886,0.72183686,0.0000015645893,0.24943927,0.023612028,0.0036266036],"study_design_scores_gemma":[0.00033545564,0.00007098009,0.00093731086,0.0000052681858,0.0013626938,0.000016434718,0.000026406668,0.60928905,4.4255185e-7,0.38680896,0.00094796147,0.0001990234],"about_ca_topic_score_codex":0.000168852,"about_ca_topic_score_gemma":0.00013259538,"teacher_disagreement_score":0.13736969,"about_ca_system_score_codex":0.00011324079,"about_ca_system_score_gemma":0.00014959865,"threshold_uncertainty_score":0.99900424},"labels":[],"label_agreement":null},{"id":"W4289732222","doi":"10.1016/j.csda.2022.107584","title":"Estimation for partial functional partially linear additive model","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Mathematics; Estimator; Scalar (mathematics); Applied mathematics; Asymptotic distribution; Functional principal component analysis; Nonlinear system; Functional data analysis; Additive model; Multivariate statistics; Nonparametric statistics; Linear model; Mathematical optimization; Econometrics; Statistics","score_opus":0.21814688525275955,"score_gpt":0.4262537220129294,"score_spread":0.20810683676016983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289732222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003506037,0.000008649188,0.9108135,0.00013511012,0.00010884186,0.00024594905,0.08823342,0.00004916836,0.00005475356],"genre_scores_gemma":[0.07084731,0.0000020617151,0.8844683,0.00018953199,0.0000971525,0.00018432442,0.044053063,0.000022026465,0.00013622733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975025,0.00022312197,0.0006228412,0.0005856613,0.0008038796,0.00026197504],"domain_scores_gemma":[0.99383265,0.0048721298,0.0003076465,0.00048178752,0.00038618897,0.000119616685],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000996539,0.00018572884,0.0003841549,0.00021204319,0.0006371443,0.00006605762,0.0003772726,0.00003533048,0.0015661466],"category_scores_gemma":[0.0032113164,0.00019926028,0.00010857734,0.0006650255,0.00008818522,0.00012815671,0.00038328214,0.00018000581,0.000013296701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005394181,0.00011335433,0.00006569922,0.000012788078,0.00044379782,0.0000019951617,0.0000450899,0.55369943,0.0000012369176,0.41191196,0.022604063,0.011046642],"study_design_scores_gemma":[0.00021904604,0.00003939744,0.0005730155,0.0000013328593,0.0009935716,0.0000011265705,0.0000121794665,0.5588151,0.0000019014375,0.4386066,0.00060689915,0.00012983807],"about_ca_topic_score_codex":0.000034101264,"about_ca_topic_score_gemma":0.000032304215,"teacher_disagreement_score":0.07049671,"about_ca_system_score_codex":0.000097013704,"about_ca_system_score_gemma":0.00028366872,"threshold_uncertainty_score":0.99934655},"labels":[],"label_agreement":null},{"id":"W4307958056","doi":"10.1016/j.csda.2022.107646","title":"A unified framework of multiply robust estimation approaches for handling incomplete data","year":2022,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institute on Minority Health and Health Disparities; National Institute of General Medical Sciences","keywords":"Imputation (statistics); Missing data; Quantile; Weighting; Computer science; Inverse probability weighting; Data mining; Population; Mathematics; Statistics; Mathematical optimization; Algorithm; Estimator","score_opus":0.38403047526707323,"score_gpt":0.4281909063231017,"score_spread":0.04416043105602846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307958056","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014405092,0.000033462184,0.907192,0.00009460835,0.00006753148,0.0003068944,0.092110604,0.000030826843,0.000020033061],"genre_scores_gemma":[0.0607257,0.0000029234952,0.88558084,0.000032835345,0.00004002398,0.000043101187,0.053542536,0.000022503187,0.000009535153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722886,0.00032766664,0.00082788814,0.00070625276,0.00067980576,0.00022953804],"domain_scores_gemma":[0.9854131,0.012244958,0.00056628574,0.0014505525,0.00024075987,0.000084388106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017202296,0.00019198516,0.00059837394,0.0002827328,0.0004356614,0.000084736246,0.0013350917,0.000046605466,0.00028852932],"category_scores_gemma":[0.0072195013,0.00020113819,0.000069168455,0.0010360223,0.00012401264,0.00016894854,0.0013208252,0.00022049197,0.0000017846869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005107987,0.00018782378,0.00043514706,0.00015848957,0.0009030377,0.0000027685196,0.00015263737,0.2615739,0.0000010493796,0.70097303,0.0024532874,0.033107713],"study_design_scores_gemma":[0.00016561201,0.000028168322,0.0008941324,0.000008823417,0.0010807279,0.0000010380836,0.000057262117,0.52582306,4.8388716e-7,0.47172835,0.00009701985,0.000115341594],"about_ca_topic_score_codex":0.00013740546,"about_ca_topic_score_gemma":0.00005323636,"teacher_disagreement_score":0.26424912,"about_ca_system_score_codex":0.000054791555,"about_ca_system_score_gemma":0.00015944641,"threshold_uncertainty_score":0.8642939},"labels":[],"label_agreement":null},{"id":"W4317934127","doi":"10.1016/j.csda.2023.107703","title":"Regularized regression for two phase failure time studies","year":2023,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Waterloo; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Covariate; Proportional hazards model; Context (archaeology); Estimator; Statistics; Accelerated failure time model; Mathematics; Sample size determination; Feature selection; Coordinate descent; Regression analysis; Econometrics; Computer science; Algorithm; Machine learning; Biology","score_opus":0.26702739295305283,"score_gpt":0.5284769810269151,"score_spread":0.26144958807386226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317934127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018452742,0.000042309523,0.9730684,0.0003914867,0.00007487614,0.0002641469,0.02414797,0.00013728149,0.000028247992],"genre_scores_gemma":[0.0034158502,0.000020690248,0.97408265,0.00007004364,0.00010219041,0.000044972952,0.021503488,0.000027669183,0.00073245325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766797,0.0002257087,0.00063666404,0.0006109708,0.00055370224,0.00030499938],"domain_scores_gemma":[0.98674196,0.01144159,0.00029526386,0.00072881556,0.00067069737,0.00012166639],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013411518,0.00022896467,0.0007019827,0.00036772172,0.00030724998,0.00009526443,0.00045733282,0.000052247713,0.0003127151],"category_scores_gemma":[0.00908892,0.00018897626,0.000111879606,0.0015438333,0.00014730629,0.00011093394,0.00036572653,0.00010832401,0.00011383483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010629307,0.00021554179,0.000093088136,0.0002052658,0.004012128,0.000034496505,0.0002570372,0.0028431767,0.00017391818,0.56254256,0.38860354,0.040912945],"study_design_scores_gemma":[0.00074298726,0.00003688024,0.00018272344,0.000020009045,0.001415449,7.4791353e-7,0.000029063382,0.51956236,0.0000063237817,0.47684062,0.0010270873,0.00013572167],"about_ca_topic_score_codex":0.000015894679,"about_ca_topic_score_gemma":0.000032294764,"teacher_disagreement_score":0.5167192,"about_ca_system_score_codex":0.000043155716,"about_ca_system_score_gemma":0.00007942262,"threshold_uncertainty_score":0.9992579},"labels":[],"label_agreement":null},{"id":"W4366144453","doi":"10.1016/j.csda.2023.107761","title":"Estimation of multivariate tail quantities","year":2023,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tail dependence; Copula (linguistics); Multivariate statistics; Quantile; Mathematics; Orthant; Asymmetry; Multivariate normal distribution; Inference; Marginal distribution; Statistics; Applied mathematics; Econometrics; Computer science; Random variable; Artificial intelligence","score_opus":0.10781657850216148,"score_gpt":0.3206000279431625,"score_spread":0.21278344944100103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366144453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04328121,0.00011983908,0.9411817,0.00006794553,0.000078134,0.000053543645,0.015047369,0.00003522429,0.00013500398],"genre_scores_gemma":[0.8262687,0.00006124632,0.15814774,0.000016030592,0.000019054463,0.0000029227056,0.015363436,0.000008583438,0.000112340815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872464,0.000017262097,0.0006798628,0.00034683364,0.00008901182,0.00014239413],"domain_scores_gemma":[0.99884194,0.00030058657,0.0003377909,0.00039578244,0.00008813846,0.000035754794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006240115,0.00009161119,0.0003628647,0.0005176511,0.00010812655,0.000046345835,0.0002645446,0.000040119023,0.00012379924],"category_scores_gemma":[0.00057707645,0.00011416216,0.000067072884,0.0012626523,0.00005426684,0.00022066117,0.000149398,0.000060466587,0.00023511155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041515646,0.00002081168,0.01551367,0.00002057834,0.00021844666,9.82695e-7,0.00013898453,0.6121844,3.6414286e-7,0.36846438,0.0009600625,0.0024731657],"study_design_scores_gemma":[0.00009067558,0.0000069095995,0.11930976,0.0000030892572,0.00007894566,6.564093e-8,0.0000087552025,0.68718857,5.644668e-7,0.19280405,0.00043105183,0.00007753965],"about_ca_topic_score_codex":0.0021893333,"about_ca_topic_score_gemma":0.00016433994,"teacher_disagreement_score":0.78303397,"about_ca_system_score_codex":0.000024381821,"about_ca_system_score_gemma":0.000031683117,"threshold_uncertainty_score":0.46553978},"labels":[],"label_agreement":null},{"id":"W4383070247","doi":"10.1016/j.csda.2023.107816","title":"Potts-Cox survival regression","year":2023,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Mathematics; Markov chain Monte Carlo; Applied mathematics; Markov chain; Laplace's method; Monte Carlo method; Statistics; Bayesian probability","score_opus":0.07695381996116518,"score_gpt":0.3729217299482058,"score_spread":0.29596790998704064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383070247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014314272,0.000054145774,0.99650806,0.00063226797,0.0002702431,0.0000643419,0.0017711108,0.00021577447,0.0003409226],"genre_scores_gemma":[0.020796021,0.00005464215,0.9699264,0.00018569407,0.00008348929,0.0000044468475,0.008515921,0.000011929776,0.00042141543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756324,0.00024987484,0.00037478944,0.0007770624,0.00073514244,0.00029989646],"domain_scores_gemma":[0.9973272,0.0008121378,0.00016016263,0.0013202399,0.00022966761,0.0001505689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010913607,0.00017727449,0.00034018524,0.00048494904,0.000252411,0.0002705998,0.0016083169,0.00005637819,0.000060299706],"category_scores_gemma":[0.00024302643,0.00015733777,0.00008539628,0.0033765878,0.000053819367,0.0004169346,0.0010949987,0.00013555492,0.00021087709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053058534,0.000053238702,0.0016917862,0.000017827155,0.0007039857,0.00010731618,0.00015559091,0.028008403,0.0000121191215,0.7103175,0.077492036,0.18143488],"study_design_scores_gemma":[0.00010649116,0.00000880674,0.021438502,0.000004632015,0.00018651,0.0000016815687,0.000002359034,0.75373363,0.000002041003,0.22208084,0.0022845552,0.0001499535],"about_ca_topic_score_codex":0.000104675535,"about_ca_topic_score_gemma":0.000052669297,"teacher_disagreement_score":0.72572523,"about_ca_system_score_codex":0.000028793273,"about_ca_system_score_gemma":0.000121190445,"threshold_uncertainty_score":0.6416048},"labels":[],"label_agreement":null},{"id":"W4391247896","doi":"10.1016/j.csda.2024.107919","title":"A unified framework of analyzing missing data and variable selection using regularized likelihood","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Missing data; Feature selection; Mathematics; Model selection; Maximum likelihood; Variable (mathematics); Statistics; Computer science; Artificial intelligence","score_opus":0.13628757786915835,"score_gpt":0.42476817451306986,"score_spread":0.2884805966439115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391247896","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011130715,0.00030298549,0.9885558,0.000052933086,0.00007254011,0.000091070426,0.009726159,0.000049644605,0.00003582808],"genre_scores_gemma":[0.037684496,0.000026204234,0.95816916,0.00002073417,0.00006649149,0.0000011972413,0.003996908,0.000022618187,0.000012159997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976786,0.00026622854,0.0006844161,0.0007090754,0.00043882255,0.0002228667],"domain_scores_gemma":[0.9919036,0.00663883,0.00022461203,0.0008301607,0.000289499,0.00011327058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015731999,0.00018356157,0.0005253702,0.00039752605,0.00017593046,0.0002900042,0.00046726418,0.000091596325,0.00024413689],"category_scores_gemma":[0.0053149303,0.00017898006,0.000036205838,0.0021671788,0.000116535746,0.00025792042,0.00054756354,0.00023419302,0.0000017923528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021571184,0.00007783976,0.0014326551,0.0004643334,0.0025041248,0.000012600587,0.00012760343,0.0042855656,0.0002254468,0.95638055,0.0011213318,0.03334636],"study_design_scores_gemma":[0.0000534592,0.0000096097165,0.00059094396,0.00009293859,0.002394834,0.000003761428,0.000009935071,0.5192732,0.0000033060426,0.47739685,0.00007363892,0.00009752129],"about_ca_topic_score_codex":0.00034518793,"about_ca_topic_score_gemma":0.00002994446,"teacher_disagreement_score":0.51498765,"about_ca_system_score_codex":0.00004368434,"about_ca_system_score_gemma":0.0002654386,"threshold_uncertainty_score":0.72985953},"labels":[],"label_agreement":null},{"id":"W4393947720","doi":"10.1016/j.csda.2024.107946","title":"A mixture of logistic skew-normal multinomial models","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Carleton University","keywords":"Multinomial logistic regression; Skew; Multinomial distribution; Logistic regression; Statistics; Mathematics; Econometrics; Computer science","score_opus":0.20448739595208382,"score_gpt":0.43320525133071397,"score_spread":0.22871785537863015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393947720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003547075,0.00009085801,0.93349314,0.0001605041,0.00005957702,0.0001432397,0.06520718,0.00010286409,0.000387953],"genre_scores_gemma":[0.5246897,0.000008705204,0.45224687,0.00002760391,0.000037881302,0.000012909214,0.022886598,0.000012389991,0.00007732433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800354,0.000077595396,0.00071511243,0.00048086996,0.0005285739,0.00019431997],"domain_scores_gemma":[0.9961597,0.0026080045,0.00016923684,0.0005774934,0.00036290585,0.0001227023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033599688,0.00018058706,0.00039294013,0.00026970817,0.00012331607,0.00011754191,0.00041921705,0.00009962521,0.0008849573],"category_scores_gemma":[0.0009028052,0.00017445468,0.00010978494,0.0011885416,0.00018265944,0.00020217619,0.00017972544,0.00022006084,0.000076662436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007941746,0.00012798411,0.00006222924,0.00013549568,0.0007397338,0.000009668355,0.00007829677,0.05369051,0.000003771217,0.9212682,0.019985398,0.003890739],"study_design_scores_gemma":[0.00008708305,0.000007148906,0.0015844043,0.000011844606,0.0011340783,0.0000016112115,0.00000942967,0.569365,0.0000018046015,0.42732733,0.0003693916,0.00010084756],"about_ca_topic_score_codex":0.00011767968,"about_ca_topic_score_gemma":0.00007903811,"teacher_disagreement_score":0.52433497,"about_ca_system_score_codex":0.00005445977,"about_ca_system_score_gemma":0.0001641746,"threshold_uncertainty_score":0.96896625},"labels":[],"label_agreement":null},{"id":"W4402042857","doi":"10.1016/j.csda.2024.108054","title":"Minimum profile Hellinger distance estimation of general covariate models","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hellinger distance; Covariate; Mathematics; Statistics; Estimation; Applied mathematics","score_opus":0.17777038817799987,"score_gpt":0.45051566701690426,"score_spread":0.2727452788389044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402042857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002565807,0.0002693911,0.9717314,0.00005345721,0.000110731766,0.00017578318,0.027138162,0.00007057826,0.00019391398],"genre_scores_gemma":[0.08963104,0.00003677916,0.90031135,0.00002301218,0.00005261635,0.000015278847,0.009567574,0.000029238252,0.00033309238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976931,0.0001357961,0.00076444057,0.00060775236,0.00057253026,0.00022634957],"domain_scores_gemma":[0.99618584,0.002631321,0.00020986196,0.0005896988,0.0002824157,0.0001008555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006235082,0.00020752555,0.00050667836,0.00024230522,0.00009664952,0.00009823561,0.00032906714,0.00005896981,0.00019170335],"category_scores_gemma":[0.0006013137,0.00019377375,0.000093846356,0.00086580496,0.00011760547,0.00034457163,0.00015812943,0.00013976889,0.000015014668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011470692,0.000046331945,0.000003949176,0.00016203691,0.00050430535,0.000010114256,0.00007574797,0.45630962,0.0000063688376,0.5268657,0.0022069027,0.013797412],"study_design_scores_gemma":[0.00006288661,0.000011390173,0.00002816359,0.000020833255,0.0008827856,8.661339e-7,0.0000031410657,0.5080706,0.000005993542,0.49071175,0.00009592966,0.00010567807],"about_ca_topic_score_codex":0.00006243896,"about_ca_topic_score_gemma":0.000024716337,"teacher_disagreement_score":0.08937447,"about_ca_system_score_codex":0.000051047497,"about_ca_system_score_gemma":0.00010803635,"threshold_uncertainty_score":0.79018646},"labels":[],"label_agreement":null},{"id":"W4403681653","doi":"10.1016/j.csda.2024.108072","title":"Bayesian grouping-Gibbs sampling estimation of high-dimensional linear model with non-sparsity","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Gibbs sampling; Bayesian probability; Mathematics; Linear model; Bayes estimator; Bayesian inference; Statistics; Computer science; Applied mathematics; Artificial intelligence; Pattern recognition (psychology); Econometrics; Algorithm","score_opus":0.11959033764803162,"score_gpt":0.40436377122204287,"score_spread":0.28477343357401125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403681653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005356409,0.000030436733,0.9830182,0.000078867095,0.000051334715,0.00012507643,0.011246571,0.000056862136,0.00003619947],"genre_scores_gemma":[0.37710133,0.0000034086781,0.6180142,0.00002442346,0.00002583551,0.0000036049742,0.004789856,0.000016600528,0.000020739366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977175,0.00009057623,0.0006378136,0.000588066,0.0007531516,0.00021287831],"domain_scores_gemma":[0.9954004,0.0033498178,0.00020957142,0.00054984057,0.00036969077,0.00012062356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006897471,0.00022128792,0.00053058186,0.0003474015,0.00014285542,0.000092668495,0.0003280339,0.00006464499,0.00018078364],"category_scores_gemma":[0.0008359217,0.00019039333,0.000066815584,0.0010622912,0.00014844333,0.0001908486,0.00021427117,0.00019555916,0.000012639844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021611047,0.00006917712,0.00014534459,0.0001639855,0.0007246831,0.000010368519,0.000060651862,0.6606808,0.0000050443164,0.32927907,0.0008222744,0.008017031],"study_design_scores_gemma":[0.000103520004,0.00003094797,0.0019790942,0.000060240338,0.0012777157,0.0000023581324,0.0000033310596,0.594725,0.000003792321,0.40167648,0.000004814141,0.0001326765],"about_ca_topic_score_codex":0.00028527714,"about_ca_topic_score_gemma":0.000073652554,"teacher_disagreement_score":0.37174493,"about_ca_system_score_codex":0.00005119327,"about_ca_system_score_gemma":0.00023595373,"threshold_uncertainty_score":0.77640146},"labels":[],"label_agreement":null},{"id":"W4403914277","doi":"10.1016/j.csda.2024.108073","title":"Multi-model subset selection","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Model selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence; Statistics","score_opus":0.03066994363911109,"score_gpt":0.2980387150845116,"score_spread":0.2673687714454005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403914277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000804721,0.00035747015,0.9928026,0.000023934008,0.00022538354,0.000060370887,0.0052224826,0.00041702864,0.00008601013],"genre_scores_gemma":[0.8380883,0.00003108013,0.15293156,0.000033330238,0.00008080241,0.000011287833,0.008515729,0.000024519302,0.0002833989],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903435,0.0000259532,0.00026952708,0.00028876038,0.00024345194,0.00013793765],"domain_scores_gemma":[0.9995039,0.00012030486,0.000019418056,0.00022123437,0.00007005249,0.00006507704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001639004,0.0001222678,0.00017807956,0.0003123911,0.000076152646,0.00020393991,0.00016950957,0.000043007145,0.00011709321],"category_scores_gemma":[0.000028350803,0.00012790038,0.000057727248,0.00096873724,0.000015956932,0.00018040105,0.000032005006,0.00011848716,0.00018423542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015783351,0.000009177137,0.00020134216,0.000039403803,0.0010578089,0.0000050947415,0.00003557324,0.97263616,0.00007492064,0.0016867404,0.020341977,0.003910211],"study_design_scores_gemma":[0.000097433636,0.0000043233877,0.0020622697,0.0000058944106,0.0006273979,0.0000038580993,0.0000049058676,0.9905781,0.0000026311766,0.000789217,0.005683716,0.0001402595],"about_ca_topic_score_codex":0.00009827791,"about_ca_topic_score_gemma":0.00052644557,"teacher_disagreement_score":0.83987105,"about_ca_system_score_codex":0.00007526315,"about_ca_system_score_gemma":0.00003741268,"threshold_uncertainty_score":0.52156264},"labels":[],"label_agreement":null},{"id":"W4408912893","doi":"10.1016/j.csda.2025.108179","title":"Sparse factor analysis for categorical data with the group-sparse generalized singular value decomposition","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Professional Staff Congress and City University of New York; Campbell Family Mental Health Research Institute; Centre for Addiction and Mental Health; National Science Foundation","keywords":"Singular value decomposition; Mathematics; Categorical variable; Group (periodic table); Sparse approximation; Applied mathematics; Value (mathematics); Combinatorics; Statistics; Algorithm; Physics","score_opus":0.05499552134827709,"score_gpt":0.3428226146050209,"score_spread":0.2878270932567438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408912893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019758474,0.00011401874,0.98696536,0.0014403248,0.00009446716,0.00027777982,0.00904553,0.000068772584,0.00001791392],"genre_scores_gemma":[0.21602379,0.000026290036,0.68886155,0.00067457627,0.00004432118,0.000027028454,0.094278306,0.000009187595,0.00005494702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971967,0.00025905494,0.0004958593,0.0011270229,0.0006238348,0.00029754045],"domain_scores_gemma":[0.9957617,0.001201731,0.00028213032,0.0022340976,0.00041230026,0.000108032575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056261336,0.00024645406,0.00049663737,0.00061325217,0.000584578,0.00061722443,0.002519042,0.00006734849,0.00004883892],"category_scores_gemma":[0.00013345065,0.0001797576,0.0001333268,0.0036803521,0.00009776769,0.00069956295,0.0010185323,0.00013654813,0.000014162373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012765352,0.00042185767,0.005280161,0.000045488843,0.015276302,0.000028986979,0.00017929438,0.72888654,0.0000628553,0.16409267,0.062220234,0.023377946],"study_design_scores_gemma":[0.00047616023,0.000029289624,0.019553807,0.000006859248,0.0059173107,0.0000013889457,0.0000113166825,0.95385855,0.00000943558,0.016395632,0.0035157632,0.0002244553],"about_ca_topic_score_codex":0.00058459945,"about_ca_topic_score_gemma":0.00067218824,"teacher_disagreement_score":0.29810378,"about_ca_system_score_codex":0.00006458518,"about_ca_system_score_gemma":0.00016367955,"threshold_uncertainty_score":0.7330302},"labels":[],"label_agreement":null},{"id":"W4411487056","doi":"10.1016/j.csda.2025.108235","title":"Enhancing approximate modular Bayesian inference by emulating the conditional posterior","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Los Alamos National Laboratory; Sandia National Laboratories; Laboratory Directed Research and Development; Research and Development; Simon Fraser University","keywords":"Inference; Posterior probability; Bayesian probability; Bayesian inference; Modular design; Computer science; Mathematics; Artificial intelligence; Machine learning; Econometrics; Programming language","score_opus":0.015057138753383492,"score_gpt":0.30322771600744497,"score_spread":0.2881705772540615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411487056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000497116,0.00013382226,0.99520296,0.0011908705,0.0000792933,0.00012586989,0.002556221,0.000072717085,0.00014115758],"genre_scores_gemma":[0.61126715,0.00000809663,0.38352364,0.0006161033,0.000018393486,0.000011739691,0.004463464,0.000005307902,0.0000860938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764615,0.00012308879,0.0005881567,0.00076645403,0.00056105346,0.00031510208],"domain_scores_gemma":[0.99730504,0.0009145969,0.00027466437,0.0010659253,0.00035162678,0.000088168985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044650325,0.00022375118,0.00031571227,0.00025322553,0.0006106224,0.0008459974,0.0021114254,0.000053238793,0.000086753265],"category_scores_gemma":[0.0003182054,0.0001852656,0.0000680508,0.0019470083,0.0001301941,0.000646227,0.0010046841,0.00019473875,0.000019998783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007146034,0.00012220358,0.0060012257,0.00011236917,0.0012921217,0.000018452005,0.00027333255,0.099673994,0.00021408573,0.8634182,0.0054190285,0.02344782],"study_design_scores_gemma":[0.000117679956,0.000009981608,0.016221095,0.000020087,0.00023938264,0.0000025774236,0.000013012407,0.8087213,0.000028670307,0.17412923,0.00032884572,0.00016813692],"about_ca_topic_score_codex":0.00014515327,"about_ca_topic_score_gemma":0.00007651029,"teacher_disagreement_score":0.7090473,"about_ca_system_score_codex":0.000050718572,"about_ca_system_score_gemma":0.00030121976,"threshold_uncertainty_score":0.81579727},"labels":[],"label_agreement":null},{"id":"W4412599868","doi":"10.1016/j.csda.2025.108253","title":"Bayesian optimization sequential surrogate (BOSS) algorithm: Fast Bayesian inference for a broad class of Bayesian hierarchical models","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Statistical Sciences Institute; Ministry of Colleges and Universities","keywords":"Bayesian probability; Boss; Bayesian inference; Inference; Computer science; Algorithm; Class (philosophy); Variable-order Bayesian network; Bayesian hierarchical modeling; Bayesian statistics; Surrogate model; Artificial intelligence; Mathematics; Machine learning; Engineering","score_opus":0.02687383401988679,"score_gpt":0.3155520691185523,"score_spread":0.2886782350986655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412599868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009618257,0.000076006036,0.9915836,0.0006770985,0.0001702746,0.00036453528,0.006712949,0.00009992943,0.0003060279],"genre_scores_gemma":[0.24668224,0.000043324402,0.7459247,0.00017560693,0.00004062129,0.00003209193,0.007012124,0.000015869065,0.00007339599],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959956,0.00019968019,0.0011725164,0.0013038297,0.0007908661,0.0005375016],"domain_scores_gemma":[0.9958743,0.0009535196,0.0005417858,0.0013670856,0.0010289514,0.00023435723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057241705,0.00040428864,0.0007736351,0.0009417118,0.0003946251,0.0005716823,0.0024919792,0.00016465811,0.00007182453],"category_scores_gemma":[0.00027705365,0.0004235606,0.00020117634,0.0031946222,0.0002522179,0.0011642845,0.0009245519,0.0002543674,0.0000033166586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019134946,0.00013724326,0.00040016216,0.00011241622,0.0006764671,0.0000076088054,0.000100307814,0.6614484,0.0000020490916,0.28118178,0.0007518966,0.055162508],"study_design_scores_gemma":[0.0004829539,0.00005250863,0.00063329726,0.00004508687,0.0005665473,0.0000022488596,0.000009725563,0.7531348,0.000009834315,0.24467556,0.00009639598,0.00029107087],"about_ca_topic_score_codex":0.00026095982,"about_ca_topic_score_gemma":0.00018020923,"teacher_disagreement_score":0.24667262,"about_ca_system_score_codex":0.000099726174,"about_ca_system_score_gemma":0.0009980281,"threshold_uncertainty_score":0.9998216},"labels":[],"label_agreement":null},{"id":"W4413049442","doi":"10.1016/j.csda.2025.108255","title":"Estimating a smooth covariance for functional data","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Science Foundation Ireland; Department of Agriculture, Food and the Marine, Ireland","keywords":"Covariance; Mathematics; Statistics; Covariance intersection; Covariance function; Computer science; Econometrics; Applied mathematics; Algorithm","score_opus":0.26623025529923344,"score_gpt":0.46800491528620997,"score_spread":0.20177465998697652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413049442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044161072,0.000045693283,0.9472968,0.00030303776,0.0002562315,0.00022079743,0.051561486,0.00005406062,0.0002177547],"genre_scores_gemma":[0.004372969,0.0000032431344,0.9574785,0.0002906698,0.00011591287,0.000027597749,0.037459217,0.000015117804,0.00023672926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99761045,0.00013670044,0.0006943362,0.000853925,0.00044254024,0.00026207467],"domain_scores_gemma":[0.98614174,0.0114275,0.00026441272,0.0015487162,0.00053229876,0.00008531348],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013366159,0.00020188872,0.00048847793,0.00026390518,0.00033123037,0.00017861508,0.0010622318,0.00006060613,0.00030947654],"category_scores_gemma":[0.013688111,0.0001994988,0.000057669313,0.001150004,0.00012416375,0.00018968302,0.0007588765,0.00014098479,0.000011996493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030200645,0.000103936814,0.00083277834,0.0001354659,0.0012448876,0.0000027161539,0.0000124547605,0.024798797,0.0000015261535,0.8378095,0.101931535,0.033096183],"study_design_scores_gemma":[0.0002031412,0.000008551843,0.005297515,0.00001692657,0.0013739881,4.3175154e-7,0.0000042092884,0.5285727,2.5912487e-7,0.46276176,0.0016555137,0.00010501914],"about_ca_topic_score_codex":0.000104110906,"about_ca_topic_score_gemma":0.00010209686,"teacher_disagreement_score":0.50377387,"about_ca_system_score_codex":0.000050122133,"about_ca_system_score_gemma":0.00030175777,"threshold_uncertainty_score":0.99462},"labels":[],"label_agreement":null},{"id":"W4416379749","doi":"10.1016/j.csda.2025.108305","title":"A semi-parametric approach to receiver operating characteristic analysis with semi-continuous biomarker","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Ovarian cancer diagnosis and treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Science Foundation of Fujian Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Receiver operating characteristic; Estimator; Biomarker; Confidence interval; Youden's J statistic; Classifier (UML); Inference; Coverage probability","score_opus":0.032349528775994,"score_gpt":0.3250317895115824,"score_spread":0.2926822607355884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416379749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020630049,0.00019116125,0.97030413,0.0005053366,0.000046981855,0.00045650388,0.006782225,0.000046225094,0.0010374088],"genre_scores_gemma":[0.695292,0.000035024048,0.26519665,0.00065363664,0.000037183054,0.000069329784,0.03822059,0.000016449943,0.00047913354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99733394,0.00010318726,0.0005996157,0.0010579684,0.0005939567,0.00031130208],"domain_scores_gemma":[0.9974315,0.00058704335,0.0002007362,0.0010200527,0.00052858057,0.00023207432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034801403,0.0003025644,0.0009989459,0.0019036881,0.00021343779,0.00022615366,0.00029834494,0.00006699208,0.00021893723],"category_scores_gemma":[0.00031976224,0.00025062432,0.00016576884,0.010480204,0.00006823231,0.00011574399,0.00020389268,0.00014424851,0.000032571064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021475802,0.0014258188,0.68481976,0.00014623368,0.0721315,0.00014226865,0.00017334789,0.20110238,0.0000093514345,0.0028211044,0.015265452,0.021748036],"study_design_scores_gemma":[0.0005916975,0.000054220924,0.52548563,0.000025601692,0.028903982,0.0000038622616,0.000026183383,0.44381866,0.0000020642635,0.00007502529,0.0008529649,0.00016009106],"about_ca_topic_score_codex":0.000889505,"about_ca_topic_score_gemma":0.000138011,"teacher_disagreement_score":0.70510745,"about_ca_system_score_codex":0.00025654072,"about_ca_system_score_gemma":0.00029135103,"threshold_uncertainty_score":0.9999946},"labels":[],"label_agreement":null},{"id":"W4416828757","doi":"10.1016/j.csda.2025.108309","title":"Parametric estimation of conditional archimedean copula generators for censored data","year":2025,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Copula (linguistics); Parametric statistics; Vine copula; Embedding; Conditional probability distribution","score_opus":0.08187733465348705,"score_gpt":0.3387920150896172,"score_spread":0.25691468043613014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416828757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008124458,0.0003729599,0.85208434,0.00009762949,0.00009498601,0.0001635238,0.13898778,0.000012399204,0.000061948755],"genre_scores_gemma":[0.47879732,0.000028072516,0.40787885,0.00004605465,0.000020788315,0.0000060265634,0.1131956,0.000005697719,0.000021575017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980898,0.000025440535,0.00097038905,0.00064324215,0.00010335671,0.00016776212],"domain_scores_gemma":[0.9976168,0.0007766923,0.00044959853,0.0009192364,0.0001891664,0.000048462753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007749132,0.00013064944,0.000499422,0.0008290093,0.00017151248,0.00006896648,0.00069079665,0.000058418165,0.000072535906],"category_scores_gemma":[0.0016346307,0.00016494209,0.00007674454,0.0013830806,0.000087391054,0.000247543,0.00027590938,0.00007763142,0.000014411044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016281132,0.000074339594,0.019326404,0.00004605515,0.00056799373,3.1100785e-7,0.000015766345,0.4732087,2.2924613e-7,0.49562553,0.006251495,0.00486691],"study_design_scores_gemma":[0.00021699443,0.000009050434,0.043416537,0.000004254576,0.00024825134,8.6288026e-8,0.0000030232559,0.6297077,0.0000014724196,0.32541037,0.000893571,0.00008869296],"about_ca_topic_score_codex":0.0005434022,"about_ca_topic_score_gemma":0.00012735234,"teacher_disagreement_score":0.47067288,"about_ca_system_score_codex":0.00005189901,"about_ca_system_score_gemma":0.0001182815,"threshold_uncertainty_score":0.67261434},"labels":[],"label_agreement":null},{"id":"W606855496","doi":"10.1016/j.csda.2003.08.004","title":"Estimating variances for all sample sizes by the bootstrap","year":2003,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bootstrapping (finance); Sample size determination; Resampling; Estimator; Statistics; Sample (material); Statistic; Variance (accounting); Mathematics; Bootstrap aggregating; Sample variance; Econometrics; Computer science","score_opus":0.2553889258680848,"score_gpt":0.4867447200362911,"score_spread":0.23135579416820629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W606855496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037365415,0.00009758592,0.96479857,0.00015964774,0.00008684469,0.00025432033,0.034429252,0.000034428307,0.0001019844],"genre_scores_gemma":[0.007823457,0.000008289592,0.98433787,0.00023067657,0.00004982064,0.00004363521,0.0074016647,0.000024222283,0.00008039357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980029,0.0002279546,0.00055275555,0.00051436457,0.00039793673,0.0003041084],"domain_scores_gemma":[0.9784416,0.02033728,0.0002847603,0.0005936288,0.00024194681,0.000100783465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011059077,0.0002004747,0.00040914008,0.0000626385,0.00036834582,0.00013259955,0.00045281387,0.00004345004,0.00020401333],"category_scores_gemma":[0.010313073,0.00015340043,0.00008402588,0.0003730429,0.00012971753,0.0001462048,0.00008582433,0.00011719728,0.0000036060137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000090342655,0.00007836141,0.00006371774,0.000045423454,0.00097409345,0.0000013326521,0.000073099545,0.07418615,0.000003649264,0.88099647,0.027641067,0.01592762],"study_design_scores_gemma":[0.00012789256,0.000014269019,0.00004384199,0.0000030032259,0.0009405719,9.510647e-7,0.000014079743,0.47922176,0.0000019005346,0.5157515,0.0037748686,0.00010539986],"about_ca_topic_score_codex":0.00008824383,"about_ca_topic_score_gemma":0.000080630016,"teacher_disagreement_score":0.40503561,"about_ca_system_score_codex":0.000030769683,"about_ca_system_score_gemma":0.00007059622,"threshold_uncertainty_score":0.99802345},"labels":[],"label_agreement":null},{"id":"W824864210","doi":"10.1016/j.csda.2015.05.009","title":"Using mixtures of<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si124.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>t</mml:mi></mml:math>densities to make inferences in the presence of missing data with a small number of multiply imputed data sets","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Economic and Social Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Inference; Stability (learning theory); Computer science; Set (abstract data type); Missing data; Algorithm; Statistics; Mathematics; Artificial intelligence; Machine learning; Programming language","score_opus":0.11865438480455953,"score_gpt":0.3682728393930382,"score_spread":0.24961845458847864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W824864210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33957496,0.000034869197,0.6470653,0.000042506443,0.000040199302,0.000049902697,0.013157518,0.000009028746,0.00002574317],"genre_scores_gemma":[0.3887014,0.000009523821,0.60646725,0.000043631455,0.000033240718,0.000005047897,0.0047206995,0.000018118159,0.0000011052214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699616,0.000293,0.0008880563,0.0005937203,0.00095263246,0.00027645574],"domain_scores_gemma":[0.99154294,0.005393243,0.00077958254,0.0018286968,0.00032862287,0.00012694925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015392681,0.00022831316,0.0004387724,0.00014795185,0.00012526088,0.00017143894,0.0016428974,0.000111986476,0.000018130542],"category_scores_gemma":[0.0051682014,0.00020162767,0.00006003065,0.0007232198,0.00037558618,0.00031111678,0.0014778934,0.00021065083,0.000006073188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015152487,0.00018281178,0.0007020068,0.00035503934,0.0007522429,0.00007328352,0.0010788274,0.0072782394,0.00003356613,0.9840832,0.0005249634,0.00478433],"study_design_scores_gemma":[0.00030116932,0.00008001866,0.0014833675,0.00027104752,0.0012488689,0.000036712936,0.00045473178,0.95347065,0.000044118675,0.042389322,0.000032560332,0.00018741655],"about_ca_topic_score_codex":0.0024049615,"about_ca_topic_score_gemma":0.0014157619,"teacher_disagreement_score":0.94619244,"about_ca_system_score_codex":0.000009120294,"about_ca_system_score_gemma":0.00052338163,"threshold_uncertainty_score":0.82221377},"labels":[],"label_agreement":null}]}